Chengzhi Zhang

Lei Zhao, Yingyi Zhang, Chengzhi Zhang

[Purpose] To understand the meaning of a sentence, humans can focus on important words in the sentence, which reflects our eyes staying on each word in different gaze time or times. Thus, some studies utilize eye-tracking values to optimize the attention mechanism in deep learning models. But these studies lack to explain the rationality of this approach. Whether the attention mechanism possesses this feature of human reading needs to be explored. [Design/methodology/approach] We conducted experiments on a sentiment classification task. Firstly, we obtained eye-tracking values from two open-source eye-tracking corpora to describe the feature of human reading. Then, the machine attention values of each sentence were learned from a sentiment classification model. Finally, a comparison was conducted to analyze machine attention values and eye-tracking values. [Findings] Through experiments, we found the attention mechanism can focus on important words, such as adjectives, adverbs, and sentiment words, which are valuable for judging the sentiment of sentences on the sentiment classification task. It possesses the feature of human reading, focusing on important words in sentences when reading. Due to the insufficient learning of the attention mechanism, some words are wrongly focused. The eye-tracking values can help the attention mechanism correct this error and improve the model performance. [Originality/value] Our research not only provides a reasonable explanation for the study of using eye-tracking values to optimize the attention mechanism, but also provides new inspiration for the interpretability of attention mechanism.

Shangchao Su, Bin Li, Chengzhi Zhang et al.

Detection models trained by one party (including server) may face severe performance degradation when distributed to other users (clients). Federated learning can enable multi-party collaborative learning without leaking client data. In this paper, we focus on a special cross-domain scenario in which the server has large-scale labeled data and multiple clients only have a small amount of labeled data; meanwhile, there exist differences in data distributions among the clients. In this case, traditional federated learning methods can't help a client learn both the global knowledge of all participants and its own unique knowledge. To make up for this limitation, we propose a cross-domain federated object detection framework, named FedOD. The proposed framework first performs the federated training to obtain a public global aggregated model through multi-teacher distillation, and sends the aggregated model back to each client for fine-tuning its personalized local model. After a few rounds of communication, on each client we can perform weighted ensemble inference on the public global model and the personalized local model. We establish a federated object detection dataset which has significant background differences and instance differences based on multiple public autonomous driving datasets, and then conduct extensive experiments on the dataset. The experimental results validate the effectiveness of the proposed method.

Yuzhuo Wang, Chengzhi Zhang, Kai Li

In scientific research, the method is an indispensable means to solve scientific problems and a critical research object. With the advancement of sciences, many scientific methods are being proposed, modified, and used in academic literature. The authors describe details of the method in the abstract and body text, and key entities in academic literature reflecting names of the method are called method entities. Exploring diverse method entities in a tremendous amount of academic literature helps scholars understand existing methods, select the appropriate method for research tasks, and propose new methods. Furthermore, the evolution of method entities can reveal the development of a discipline and facilitate knowledge discovery. Therefore, this article offers a systematic review of methodological and empirical works focusing on extracting method entities from full-text academic literature and efforts to build knowledge services using these extracted method entities. Definitions of key concepts involved in this review were first proposed. Based on these definitions, we systematically reviewed the approaches and indicators to extract and evaluate method entities, with a strong focus on the pros and cons of each approach. We also surveyed how extracted method entities are used to build new applications. Finally, limitations in existing works as well as potential next steps were discussed.

Hongye Zhao, Yi Zhao, Chengzhi Zhang

Academia and industry each possess distinct advantages in advancing technological progress. Academia's core mission is to promote open dissemination of research results and drive disciplinary progress. The industry values knowledge appropriability and core competitiveness, yet actively engages in open practices like academic conferences and platform sharing, creating a knowledge strategy paradox. Highly novel and publicly accessible knowledge serves as the driving force behind technological advancement. However, it remains unclear whether industry or academia can produce more novel research outcomes. Some studies argue that academia tends to generate more novel ideas, while others suggest that industry researchers are more likely to drive breakthroughs. Previous studies have been limited by data sources and inconsistent measures of novelty. To address these gaps, this study conducts an analysis using four types of fine-grained knowledge entities (Method, Tool, Dataset, Metric), calculates semantic distances between entities within a unified semantic space to quantify novelty, and achieves comparability of novelty across different types of literature. Then, a regression model is constructed to analyze the differences in publication novelty between industry and academia. The results indicate that academia demonstrates higher novelty outputs, which is particularly evident in patents. At the entity level, both academia and industry emphasize method-driven advancements in papers, while industry holds a unique advantage in datasets. Additionally, academia-industry collaboration has a limited effect on enhancing the novelty of research papers, but it helps to enhance the novelty of patents. We release our data and associated codes at https://github.com/tinierZhao/entity_novelty.

Chengzhi Zhang, Yi Xiang, Wenke Hao et al.

Future work sentences (FWS) are the particular sentences in academic papers that contain the author's description of their proposed follow-up research direction. This paper presents methods to automatically extract FWS from academic papers and classify them according to the different future directions embodied in the paper's content. FWS recognition methods will enable subsequent researchers to locate future work sentences more accurately and quickly and reduce the time and cost of acquiring the corpus. The current work on automatic identification of future work sentences is relatively small, and the existing research cannot accurately identify FWS from academic papers, and thus cannot conduct data mining on a large scale. Furthermore, there are many aspects to the content of future work, and the subdivision of the content is conducive to the analysis of specific development directions. In this paper, Nature Language Processing (NLP) is used as a case study, and FWS are extracted from academic papers and classified into different types. We manually build an annotated corpus with six different types of FWS. Then, automatic recognition and classification of FWS are implemented using machine learning models, and the performance of these models is compared based on the evaluation metrics. The results show that the Bernoulli Bayesian model has the best performance in the automatic recognition task, with the Macro F1 reaching 90.73%, and the SCIBERT model has the best performance in the automatic classification task, with the weighted average F1 reaching 72.63%. Finally, we extract keywords from FWS and gain a deep understanding of the key content described in FWS, and we also demonstrate that content determination in FWS will be reflected in the subsequent research work by measuring the similarity between future work sentences and the abstracts.

Hongye Zhao, Yi Zhao, Chengzhi Zhang

The academia and industry are characterized by a reciprocal shaping and dynamic feedback mechanism. Despite distinct institutional logics, they have adapted closely in collaborative publishing and talent mobility, demonstrating tension between institutional divergence and intensive collaboration. Existing studies on their knowledge proximity mainly rely on macro indicators such as the number of collaborative papers or patents, lacking an analysis of knowledge units in the literature. This has led to an insufficient grasp of fine-grained knowledge proximity between industry and academia, potentially undermining collaboration frameworks and resource allocation efficiency. To remedy the limitation, this study quantifies the trajectory of academia-industry co-evolution through fine-grained entities and semantic space. In the entity measurement part, we extract fine-grained knowledge entities via pre-trained models, measure sequence overlaps using cosine similarity, and analyze topological features through complex network analysis. At the semantic level, we employ unsupervised contrastive learning to quantify convergence in semantic spaces by measuring cross-institutional textual similarities. Finally, we use citation distribution patterns to examine correlations between bidirectional knowledge flows and similarity. Analysis reveals that knowledge proximity between academia and industry rises, particularly following technological change. This provides textual evidence of bidirectional adaptation in co-evolution. Additionally, academia's knowledge dominance weakens during technological paradigm shifts. The dataset and code for this paper can be accessed at https://github.com/tinierZhao/Academic-Industrial-associations.

Chenglei Qin, Chengzhi Zhang

Purpose The purpose of this paper is to explore which structures of academic articles referees would pay more attention to, what specific content referees focus on, and whether the distribution of PRC is related to the citations. Design/methodology/approach Firstly, utilizing the feature words of section title and hierarchical attention network model (HAN) to identify the academic article structures. Secondly, analyzing the distribution of PRC in different structures according to the position information extracted by rules in PRC. Thirdly, analyzing the distribution of feature words of PRC extracted by the Chi-square test and TF-IDF in different structures. Finally, four correlation analysis methods are used to analyze whether the distribution of PRC in different structures is correlated to the citations. Findings The count of PRC distributed in Materials and Methods and Results section is significantly more than that in the structure of Introduction and Discussion, indicating that referees pay more attention to the Material and Methods and Results. The distribution of feature words of PRC in different structures is obviously different, which can reflect the content of referees' concern. There is no correlation between the distribution of PRC in different structures and the citations. Research limitations/implications Due to the differences in the way referees write peer review reports, the rules used to extract position information cannot cover all PRC. Originality/value The paper finds a pattern in the distribution of PRC in different academic article structures proving the long-term empirical understanding. It also provides insight into academic article writing: researchers should ensure the scientificity of methods and the reliability of results when writing academic article to obtain a high degree of recognition from referees.

Yuwen Lu, Ziang Tong, Qinyi Zhao et al.

The recent advances in Large Language Models (LLMs) have stimulated interest among researchers and industry professionals, particularly in their application to tasks concerning mobile user interfaces (UIs). This position paper investigates the use of LLMs for UI layout generation. Central to our exploration is the introduction of UI grammar -- a novel approach we proposed to represent the hierarchical structure inherent in UI screens. The aim of this approach is to guide the generative capacities of LLMs more effectively and improve the explainability and controllability of the process. Initial experiments conducted with GPT-4 showed the promising capability of LLMs to produce high-quality user interfaces via in-context learning. Furthermore, our preliminary comparative study suggested the potential of the grammar-based approach in improving the quality of generative results in specific aspects.

Chenglei Qin, Chengzhi Zhang, Yi Bu

[Purpose] To better understand the online reviews and help potential consumers, businessmen, and product manufacturers effectively obtain users' evaluation on product aspects, this paper explores the distribution regularities of user attention and sentiment toward product aspects from the temporal perspective of online reviews. [Design/methodology/approach] Temporal characteristics of online reviews (purchase time, review time, and time intervals between purchase time and review time), similar attributes clustering, and attribute-level sentiment computing technologies are employed based on more than 340k smartphone reviews of three products from JD.COM (a famous online shopping platform in China) to explore the distribution regularities of user attention and sentiment toward product aspects in this article. [Findings] The empirical results show that a power-law distribution can fit user attention to product aspects, and the reviews posted in short time intervals contain more product aspects. Besides, the results show that the values of user sentiment of product aspects are significantly higher/lower in short time intervals which contribute to judging the advantages and weaknesses of a product. [Research limitations] The paper can't acquire online reviews for more products with temporal characteristics to verify the findings because of the restriction on reviews crawling by the shopping platforms. [Originality/value] This work reveals the distribution regularities of user attention and sentiment toward product aspects, which is of great significance in assisting decision-making, optimizing review presentation, and improving the shopping experience.

Liang Tian, Chengzhi Zhang

COVID-19 has had a profound impact on the lives of all human beings. Emerging technologies have made significant contributions to the fight against the pandemic. An extensive review of the application of technology will help facilitate future research and technology development to provide better solutions for future pandemics. In contrast to the extensive surveys of academic communities that have already been conducted, this study explores the IT community of practice. Using GitHub as the study target, we analyzed the main functionalities of the projects submitted during the pandemic. This study examines trends in projects with different functionalities and the relationship between functionalities and technologies. The study results show an imbalance in the number of projects with varying functionalities in the GitHub community, i.e., applications account for more than half of the projects. In contrast, other data analysis and AI projects account for a smaller share. This differs significantly from the survey of the academic community, where the findings focus more on cutting-edge technologies while projects in the community of practice use more mature technologies. The spontaneous behavior of developers may lack organization and make it challenging to target needs.

Wenqing Wu, Yi Zhao, Yuzhuo Wang et al.

Novelty is a core requirement in academic publishing and a central focus of peer review, yet the growing volume of submissions has placed increasing pressure on human reviewers. While large language models (LLMs), including those fine-tuned on peer review data, have shown promise in generating review comments, the absence of a dedicated benchmark has limited systematic evaluation of their ability to assess research novelty. To address this gap, we introduce NovBench, the first large-scale benchmark designed to evaluate LLMs' capability to generate novelty evaluations in support of human peer review. NovBench comprises 1,684 paper-review pairs from a leading NLP conference, including novelty descriptions extracted from paper introductions and corresponding expert-written novelty evaluations. We focus on both sources because the introduction provides a standardized and explicit articulation of novelty claims, while expert-written novelty evaluations constitute one of the current gold standards of human judgment. Furthermore, we propose a four-dimensional evaluation framework (including Relevance, Correctness, Coverage, and Clarity) to assess the quality of LLM-generated novelty evaluations. Extensive experiments on both general and specialized LLMs under different prompting strategies reveal that current models exhibit limited understanding of scientific novelty, and that fine--tuned models often suffer from instruction-following deficiencies. These findings underscore the need for targeted fine-tuning strategies that jointly improve novelty comprehension and instruction adherence.

Yi Zhao, Yang Chenggang, Yuzhuo Wang et al.

Scientific novelty drives advances at the research frontier, yet it is also associated with heightened uncertainty and potential resistance from incumbent paradigms, leading to complex patterns of scientific impact. Prior studies have primarily ex-amined the relationship between a single dimension of novelty -- such as theoreti-cal, methodological, or results-based novelty -- and scientific impact. However, because scientific novelty is inherently multidimensional, focusing on isolated dimensions may obscure how different types of novelty jointly shape impact. Consequently, we know little about how combinations of novelty types influence scientific impact. To this end, we draw on a dataset of 15,322 articles published in Nature Communications. Using the DeepSeek-V3 model, we classify articles into three novelty dimensions based on the content of their Introduction sections: theoretical novelty, methodological novelty, and results-based novelty. These dimensions may coexist within the same article, forming distinct novelty configura-tions. Scientific impact is measured using five-year citation counts and indicators of whether an article belongs to the top 1% or top 10% highly cited papers. Descriptive results indicate that results-based novelty alone and the simultaneous presence of all three novelty types are the dominant configurations in the sample. Regression results further show that articles with results-based novelty only re-ceive significantly more citations and are more likely to rank among the top 1% and top 10% highly cited papers than articles exhibiting all three novelty types. These findings advance our understanding of how multidimensional novelty configurations shape knowledge diffusion.

Shuai Chen, Chengzhi Zhang

Scientific progress depends on the continual generation of innovative re-search ideas. However, the rapid growth of scientific literature has greatly increased the cost of knowledge filtering, making it harder for researchers to identify novel directions. Although existing large language model (LLM)-based methods show promise in research idea generation, the ideas they produce are often repetitive and lack depth. To address this issue, this study proposes a multi-agent iterative planning search strategy inspired by com-binatorial innovation theory. The framework combines iterative knowledge search with an LLM-based multi-agent system to generate, evaluate, and re-fine research ideas through repeated interaction, with the goal of improving idea diversity and novelty. Experiments in the natural language processing domain show that the proposed method outperforms state-of-the-art base-lines in both diversity and novelty. Further comparison with ideas derived from top-tier machine learning conference papers indicates that the quality of the generated ideas falls between that of accepted and rejected papers. These results suggest that the proposed framework is a promising approach for supporting high-quality research idea generation. The source code and dataset used in this paper are publicly available on Github repository: https://github.com/ChenShuai00/MAGenIdeas. The demo is available at https://huggingface.co/spaces/cshuai20/MAGenIdeas.

Tong Bao, Heng Zhang, Chengzhi Zhang

Abstractive summarization of scientific papers has always been a research focus, yet existing methods face two main challenges. First, most summarization models rely on Encoder-Decoder architectures that treat papers as sequences of words, thus fail to fully capture the structured information inherent in scientific papers. Second, existing research often use keyword mapping or feature engineering to identify the structural information, but these methods struggle with the structural flexibility of scientific papers and lack robustness across different disciplines. To address these challenges, we propose a two-stage abstractive summarization framework that leverages automatic recognition of structural functions within scientific papers. In the first stage, we standardize chapter titles from numerous scientific papers and construct a large-scale dataset for structural function recognition. A classifier is then trained to automatically identify the key structural components (e.g., Background, Methods, Results, Discussion), which provides a foundation for generating more balanced summaries. In the second stage, we employ Longformer to capture rich contextual relationships across sections and generating context-aware summaries. Experiments conducted on two domain-specific scientific paper summarization datasets demonstrate that our method outperforms advanced baselines, and generates more comprehensive summaries. The code and dataset can be accessed at https://github.com/tongbao96/code-for-SFR-AS.

Yi Xiang, Chengzhi Zhang

Automatic keyword extraction from academic papers is a key area of interest in natural language processing and information retrieval. Although previous research has mainly focused on utilizing abstract and references for keyword extraction, this paper focuses on the highlights section - a summary describing the key findings and contributions, offering readers a quick overview of the research. Our observations indicate that highlights contain valuable keyword information that can effectively complement the abstract. To investigate the impact of incorporating highlights into unsupervised keyword extraction, we evaluate three input scenarios: using only the abstract, the highlights, and a combination of both. Experiments conducted with four unsupervised models on Computer Science (CS), Library and Information Science (LIS) datasets reveal that integrating the abstract with highlights significantly improves extraction performance. Furthermore, we examine the differences in keyword coverage and content between abstract and highlights, exploring how these variations influence extraction outcomes. The data and code are available at https://github.com/xiangyi-njust/Highlight-KPE.

Wenqing Wu, Chengzhi Zhang, Tong Bao et al.

Novelty is a core component of academic papers, and there are multiple perspectives on the assessment of novelty. Existing methods often focus on word or entity combinations, which provide limited insights. The content related to a paper's novelty is typically distributed across different core sections, e.g., Introduction, Methodology and Results. Therefore, exploring the optimal combination of sections for evaluating the novelty of a paper is important for advancing automated novelty assessment. In this paper, we utilize different combinations of sections from academic papers as inputs to drive language models to predict novelty scores. We then analyze the results to determine the optimal section combinations for novelty score prediction. We first employ natural language processing techniques to identify the sectional structure of academic papers, categorizing them into introduction, methods, results, and discussion (IMRaD). Subsequently, we used different combinations of these sections (e.g., introduction and methods) as inputs for pretrained language models (PLMs) and large language models (LLMs), employing novelty scores provided by human expert reviewers as ground truth labels to obtain prediction results. The results indicate that using introduction, results and discussion is most appropriate for assessing the novelty of a paper, while the use of the entire text does not yield significant results. Furthermore, based on the results of the PLMs and LLMs, the introduction and results appear to be the most important section for the task of novelty score prediction. The code and dataset for this paper can be accessed at https://github.com/njust-winchy/SC4ANM.

Yi Zhao, Yongjun Zhu, Donghun Kim et al.

The influence of gender diversity on the success of scientific teams is of great interest to academia. However, prior findings remain inconsistent, and most studies operationalize diversity in aggregate terms, overlooking internal role differentiation. This limitation obscures a more nuanced understanding of how gender diversity shapes team impact. In particular, the effect of gender diversity across different team roles remains poorly understood. To this end, we define a scientific team as all coauthors of a paper and measure team impact through five-year citation counts. Using author contribution statements, we classified members into leadership and support roles. Drawing on more than 130,000 papers from PLOS journals, most of which are in biomedical-related disciplines, we employed multivariable regression to examine the association between gender diversity in these roles and team impact. Furthermore, we apply a threshold regression model to investigate how team size moderates this relationship. The results show that (1) the relationship between gender diversity and team impact follows an inverted U-shape for both leadership and support groups; (2) teams with an all-female leadership group and an all-male support group achieve higher impact than other team types. Interestingly, (3) the effect of leadership-group gender diversity is significantly negative for small teams but becomes positive and statistically insignificant in large teams. In contrast, the estimates for support-group gender diversity remain significant and positive, regardless of team size.

Chengzhi Zhang, Xinyi Yan, Lei Zhao et al.

The exponential increase in academic papers has significantly increased the time required for researchers to access relevant literature. Keyphrase Extraction (KPE) offers a solution to this situation by enabling researchers to efficiently retrieve relevant literature. The current study on KPE from academic articles aims to improve the performance of extraction models through innovative approaches using Title and Abstract as input corpora. However, the semantic richness of keywords is significantly constrained by the length of the abstract. While full-text-based KPE can address this issue, it simultaneously introduces noise, which significantly diminishes KPE performance. To address this issue, this paper utilized the structural features and section texts obtained from the section structure information of academic articles to extract keyphrase from academic papers. The approach consists of two main parts: (1) exploring the effect of seven structural features on KPE models, and (2) integrating the extraction results from all section texts used as input corpora for KPE models via a keyphrase integration algorithm to obtain the keyphrase integration result. Furthermore, this paper also examined the effect of the classification quality of section structure on the KPE performance. The results show that incorporating structural features improves KPE performance, though different features have varying effects on model efficacy. The keyphrase integration approach yields the best performance, and the classification quality of section structure can affect KPE performance. These findings indicate that using the section structure information of academic articles contributes to effective KPE from academic articles. The code and dataset supporting this study are available at https://github.com/yan-xinyi/SSB_KPE.

Haixu Xi, Heng Zhang, Chengzhi Zhang

In the era of explosive growth in academic literature, the burden of literature review on scholars are increasing. Proactively recommending academic papers that align with scholars' literature needs in the research process has become one of the crucial pathways to enhance research efficiency and stimulate innovative thinking. Current academic paper recommendation systems primarily focus on broad and coarse-grained suggestions based on general topic or field similarities. While these systems effectively identify related literature, they fall short in addressing scholars' more specific and fine-grained needs, such as locating papers that utilize particular research methods, or tackle distinct research tasks within the same topic. To meet the diverse and specific literature needs of scholars in the research process, this paper proposes a novel academic paper recommendation method. This approach embeds multidimensional information by integrating new types of fine-grained knowledge entities, title and abstract of document, and citation data. Recommendations are then generated by calculating the similarity between combined paper vectors. The proposed recommendation method was evaluated using the STM-KG dataset, a knowledge graph that incorporates scientific concepts derived from papers across ten distinct domains. The experimental results indicate that our method outperforms baseline models, achieving an average precision of 27.3% among the top 50 recommendations. This represents an improvement of 6.7% over existing approaches.

Heng Zhang, Chengzhi Zhang

The automated generation of research workflows is essential for improving the reproducibility of research and accelerating the paradigm of "AI for Science". However, existing methods typically extract merely fragmented procedural components and thus fail to capture complete research workflows. To address this gap, we propose an end-to-end framework that generates comprehensive, structured research workflows by mining full-text academic papers. As a case study in the Natural Language Processing (NLP) domain, our paragraph-centric approach first employs Positive-Unlabeled (PU) Learning with SciBERT to identify workflow-descriptive paragraphs, achieving an F1-score of 0.9772. Subsequently, we utilize Flan-T5 with prompt learning to generate workflow phrases from these paragraphs, yielding ROUGE-1, ROUGE-2, and ROUGE-L scores of 0.4543, 0.2877, and 0.4427, respectively. These phrases are then systematically categorized into data preparation, data processing, and data analysis stages using ChatGPT with few-shot learning, achieving a classification precision of 0.958. By mapping categorized phrases to their document locations in the documents, we finally generate readable visual flowcharts of the entire research workflows. This approach facilitates the analysis of workflows derived from an NLP corpus and reveals key methodological shifts over the past two decades, including the increasing emphasis on data analysis and the transition from feature engineering to ablation studies. Our work offers a validated technical framework for automated workflow generation, along with a novel, process-oriented perspective for the empirical investigation of evolving scientific paradigms. Source code and data are available at: https://github.com/ZH-heng/research_workflow.

Decheng Duan, Yingyi Zhang, Jitong Peng et al.

Structured information extraction from scientific literature is crucial for capturing core concepts and emerging trends in specialized fields. While existing datasets aid model development, most focus on specific publication sections due to domain complexity and the high cost of annotating scientific texts. To address this limitation, we introduce SciNLP--a specialized benchmark for full-text entity and relation extraction in the Natural Language Processing (NLP) domain. The dataset comprises 60 manually annotated full-text NLP publications, covering 7,072 entities and 1,826 relations. Compared to existing research, SciNLP is the first dataset providing full-text annotations of entities and their relationships in the NLP domain. To validate the effectiveness of SciNLP, we conducted comparative experiments with similar datasets and evaluated the performance of state-of-the-art supervised models on this dataset. Results reveal varying extraction capabilities of existing models across academic texts of different lengths. Cross-comparisons with existing datasets show that SciNLP achieves significant performance improvements on certain baseline models. Using models trained on SciNLP, we implemented automatic construction of a fine-grained knowledge graph for the NLP domain. Our KG has an average node degree of 3.2 per entity, indicating rich semantic topological information that enhances downstream applications. The dataset is publicly available at: https://github.com/AKADDC/SciNLP.

Yingyi Zhang, Chengzhi Zhang

The premise of manual keyphrase annotation is to read the corresponding content of an annotated object. Intuitively, when we read, more important words will occupy a longer reading time. Hence, by leveraging human reading time, we can find the salient words in the corresponding content. However, previous studies on keyphrase extraction ignore human reading features. In this article, we aim to leverage human reading time to extract keyphrases from microblog posts. There are two main tasks in this study. One is to determine how to measure the time spent by a human on reading a word. We use eye fixation durations extracted from an open source eye-tracking corpus (OSEC). Moreover, we propose strategies to make eye fixation duration more effective on keyphrase extraction. The other task is to determine how to integrate human reading time into keyphrase extraction models. We propose two novel neural network models. The first is a model in which the human reading time is used as the ground truth of the attention mechanism. In the second model, we use human reading time as the external feature. Quantitative and qualitative experiments show that our proposed models yield better performance than the baseline models on two microblog datasets.

Yi Zhao, Chengzhi Zhang

Novelty evaluation is vital for the promotion and management of innovation. With the advancement of information techniques and the open data movement, some progress has been made in novelty measurements. Tracking and reviewing novelty measures provides a data-driven way to assess contributions, progress, and emerging directions in the science field. As academic papers serve as the primary medium for the dissemination, validation, and discussion of scientific knowledge, this review aims to offer a systematic analysis of novelty measurements for scientific papers. We began by comparing the differences between scientific novelty and four similar concepts, including originality, scientific innovation, creativity, and scientific breakthrough. Next, we reviewed the types of scientific novelty. Then, we classified existing novelty measures according to data types and reviewed the measures for each type. Subsequently, we surveyed the approaches employed in validating novelty measures and examined the current tools and datasets associated with these measures. Finally, we proposed several open issues for future studies.

Wenqing Wu, Haixu Xi, Chengzhi Zhang

Peer review is vital in academia for evaluating research quality. Top AI conferences use reviewer confidence scores to ensure review reliability, but existing studies lack fine-grained analysis of text-score consistency, potentially missing key details. This work assesses consistency at word, sentence, and aspect levels using deep learning and NLP conference review data. We employ deep learning to detect hedge sentences and aspects, then analyze report length, hedge word/sentence frequency, aspect mentions, and sentiment to evaluate text-score alignment. Correlation, significance, and regression tests examine confidence scores' impact on paper outcomes. Results show high text-score consistency across all levels, with regression revealing higher confidence scores correlate with paper rejection, validating expert assessments and peer review fairness.

Jiayi Hao, Chengzhi Zhang

Research methods constitute an indispensable tool for scholars engaged in scientific inquiry. Investigating how scholars use research methods throughout their careers can reveal distinct patterns in method adoption, providing valuable insights for novice researchers in selecting appropriate methods. This study employs a comprehensive dataset comprising full-text journal articles and bibliographic records from the Library and Information Science (LIS) domain. Utilizing an automated classification model based on full-text cognitive analysis, the research methods employed by LIS scholars are systematically identified. Topic modeling was then conducted using Top2Vec. Subsequently, author name disambiguation is performed, and academic age is calculated for each scholar. This study focuses on 435 senior scholars with an academic age of more than 14 years and a consistent publication record at five-year intervals, covering a total of 6,116 articles. The corpus covers 16 research method categories and 20 research topics. The findings indicate that bibliometric methods are the most frequently used across career stages, accounting for 19.61% among early-career scholars and 31.81% among senior scholars. Over the course of a scholarly career, the diversity of research methods initially increases and then declines. Furthermore, scholars exhibit a propensity for combining multiple research methods, including both conventional and unconventional pairings. Notably, the research methods most commonly used by researchers change with age and seniority.

Wenqing Wu, Chengzhi Zhang, Yi Zhao et al.

With the rapid advancement of Large Language Models (LLMs), the academic community has faced unprecedented disruptions, particularly in the realm of academic communication. The primary function of peer review is improving the quality of academic manuscripts, such as clarity, originality and other evaluation aspects. Although prior studies suggest that LLMs are beginning to influence peer review, it remains unclear whether they are altering its core evaluative functions. Moreover, the extent to which LLMs affect the linguistic form, evaluative focus, and recommendation-related signals of peer-review reports has yet to be systematically examined. In this study, we examine the changes in peer review reports for academic articles following the emergence of LLMs, emphasizing variations at fine-grained level. Specifically, we investigate linguistic features such as the length and complexity of words and sentences in review comments, while also automatically annotating the evaluation aspects of individual review sentences. We also use a maximum likelihood estimation method, previously established, to identify review reports that potentially have modified or generated by LLMs. Finally, we assess the impact of evaluation aspects mentioned in LLM-assisted review reports on the informativeness of recommendation for paper decision-making. The results indicate that following the emergence of LLMs, peer review texts have become longer and more fluent, with increased emphasis on summaries and surface-level clarity, as well as more standardized linguistic patterns, particularly reviewers with lower confidence score. At the same time, attention to deeper evaluative dimensions, such as originality, replicability, and nuanced critical reasoning, has declined.

Shutian Ma, Chengzhi Zhang, Heng Zhang et al.

Citation recommendation aims to locate the important papers for scholars to cite. When writing the citing sentences, the authors usually hold different citing intents, which are referred to citation function in citation analysis. Since argumentative zoning is to identify the argumentative and rhetorical structure in scientific literature, we want to use this information to improve the citation recommendation task. In this paper, a multi-task learning model is built for citation recommendation and argumentative zoning classification. We also generated an annotated corpus of the data from PubMed Central based on a new argumentative zoning schema. The experimental results show that, by considering the argumentative information in the citing sentence, citation recommendation model will get better performance.

Tong Bao, Mir Tafseer Nayeem, Davood Rafiei et al.

Automatic survey generation has emerged as a key task in scientific document processing. While large language models (LLMs) have shown promise in generating survey texts, the lack of standardized evaluation datasets critically hampers rigorous assessment of their performance against human-written surveys. In this work, we present SurveyGen, a large-scale dataset comprising over 4,200 human-written surveys across diverse scientific domains, along with 242,143 cited references and extensive quality-related metadata for both the surveys and the cited papers. Leveraging this resource, we build QUAL-SG, a novel quality-aware framework for survey generation that enhances the standard Retrieval-Augmented Generation (RAG) pipeline by incorporating quality-aware indicators into literature retrieval to assess and select higher-quality source papers. Using this dataset and framework, we systematically evaluate state-of-the-art LLMs under varying levels of human involvement - from fully automatic generation to human-guided writing. Experimental results and human evaluations show that while semi-automatic pipelines can achieve partially competitive outcomes, fully automatic survey generation still suffers from low citation quality and limited critical analysis.

Tong Bao, Yi Zhao, Jin Mao et al.

Large Language Models (LLMs), such as ChatGPT, have prompted academic concerns about their impact on academic writing. Existing studies have primarily examined LLM usage in academic writing through quantitative approaches, such as word frequency statistics and probability-based analyses. However, few have systematically examined the potential impact of LLMs on the linguistic characteristics of academic writing. To address this gap, we conducted a large-scale analysis across 823,798 abstracts published in last decade from arXiv dataset. Through the linguistic analysis of features such as the frequency of LLM-preferred words, lexical complexity, syntactic complexity, cohesion, readability and sentiment, the results indicate a significant increase in the proportion of LLM-preferred words in abstracts, revealing the widespread influence of LLMs on academic writing. Additionally, we observed an increase in lexical complexity and sentiment in the abstracts, but a decrease in syntactic complexity, suggesting that LLMs introduce more new vocabulary and simplify sentence structure. However, the significant decrease in cohesion and readability indicates that abstracts have fewer connecting words and are becoming more difficult to read. Moreover, our analysis reveals that scholars with weaker English proficiency were more likely to use the LLMs for academic writing, and focused on improving the overall logic and fluency of the abstracts. Finally, at discipline level, we found that scholars in Computer Science showed more pronounced changes in writing style, while the changes in Mathematics were minimal.

Wenqing Wu, Chengzhi Zhang, Yi Zhao

Novelty is a crucial criterion in the peer review process for evaluating academic papers. Traditionally, it's judged by experts or measure by unique reference combinations. Both methods have limitations: experts have limited knowledge, and the effectiveness of the combination method is uncertain. Moreover, it's unclear if unique citations truly measure novelty. The large language model (LLM) possesses a wealth of knowledge, while human experts possess judgment abilities that the LLM does not possess. Therefore, our research integrates the knowledge and abilities of LLM and human experts to address the limitations of novelty assessment. One of the most common types of novelty in academic papers is the introduction of new methods. In this paper, we propose leveraging human knowledge and LLM to assist pretrained language models (PLMs, e.g. BERT etc.) in predicting the method novelty of papers. Specifically, we extract sentences related to the novelty of the academic paper from peer review reports and use LLM to summarize the methodology section of the academic paper, which are then used to fine-tune PLMs. In addition, we have designed a text-guided fusion module with novel Sparse-Attention to better integrate human and LLM knowledge. We compared the method we proposed with a large number of baselines. Extensive experiments demonstrate that our method achieves superior performance.

Bowen Ma, Chengzhi Zhang, Yuzhuo Wang et al.

With the enrichment of literature resources, researchers are facing the growing problem of information explosion and knowledge overload. To help scholars retrieve literature and acquire knowledge successfully, clarifying the semantic structure of the content in academic literature has become the essential research question. In the research on identifying the structure function of chapters in academic articles, only a few studies used the deep learning model and explored the optimization for feature input. This limits the application, optimization potential of deep learning models for the research task. This paper took articles of the ACL conference as the corpus. We employ the traditional machine learning models and deep learning models to construct the classifiers based on various feature input. Experimental results show that (1) Compared with the chapter content, the chapter title is more conducive to identifying the structure function of academic articles. (2) Relative position is a valuable feature for building traditional models. (3) Inspired by (2), this paper further introduces contextual information into the deep learning models and achieved significant results. Meanwhile, our models show good migration ability in the open test containing 200 sampled non-training samples. We also annotated the ACL main conference papers in recent five years based on the best practice performing models and performed a time series analysis of the overall corpus. This work explores and summarizes the practical features and models for this task through multiple comparative experiments and provides a reference for related text classification tasks. Finally, we indicate the limitations and shortcomings of the current model and the direction of further optimization.

Chengzhi Zhang, Lei Zhao, Mengyuan Zhao et al.

With the development of Internet technology, the phenomenon of information overload is becoming more and more obvious. It takes a lot of time for users to obtain the information they need. However, keyphrases that summarize document information highly are helpful for users to quickly obtain and understand documents. For academic resources, most existing studies extract keyphrases through the title and abstract of papers. We find that title information in references also contains author-assigned keyphrases. Therefore, this article uses reference information and applies two typical methods of unsupervised extraction methods (TF*IDF and TextRank), two representative traditional supervised learning algorithms (Naïve Bayes and Conditional Random Field) and a supervised deep learning model (BiLSTM-CRF), to analyze the specific performance of reference information on keyphrase extraction. It is expected to improve the quality of keyphrase recognition from the perspective of expanding the source text. The experimental results show that reference information can increase precision, recall, and F1 of automatic keyphrase extraction to a certain extent. This indicates the usefulness of reference information on keyphrase extraction of academic papers and provides a new idea for the following research on automatic keyphrase extraction.

Qingqing Zhou, Chengzhi Zhang

The surge in the number of books published makes the manual evaluation methods difficult to efficiently evaluate books. The use of books' citations and alternative evaluation metrics can assist manual evaluation and reduce the cost of evaluation. However, most existing evaluation research was based on a single evaluation source with coarse-grained analysis, which may obtain incomprehensive or one-sided evaluation results of book impact. Meanwhile, relying on a single resource for book assessment may lead to the risk that the evaluation results cannot be obtained due to the lack of the evaluation data, especially for newly published books. Hence, this paper measured book impact based on an evaluation system constructed by integrating multiple evaluation sources. Specifically, we conducted finer-grained mining on the multiple evaluation sources, including books' internal evaluation resources and external evaluation resources. Various technologies (e.g. topic extraction, sentiment analysis, text classification) were used to extract corresponding evaluation metrics from the internal and external evaluation resources. Then, Expert evaluation combined with analytic hierarchy process was used to integrate the evaluation metrics and construct a book impact evaluation system. Finally, the reliability of the evaluation system was verified by comparing with the results of expert evaluation, detailed and diversified evaluation results were then obtained. The experimental results reveal that differential evaluation resources can measure the books' impacts from different dimensions, and the integration of multiple evaluation data can assess books more comprehensively. Meanwhile, the book impact evaluation system can provide personalized evaluation results according to the users' evaluation purposes. In addition, the disciplinary differences should be considered for assessing books' impacts.

Qingqing Zhou, Chengzhi Zhang

The global spread of COVID-19 has caused pandemics to be widely discussed. This is evident in the large number of scientific articles and the amount of user-generated content on social media. This paper aims to compare academic communication and social communication about the pandemic from the perspective of communication preference differences. It aims to provide information for the ongoing research on global pandemics, thereby eliminating knowledge barriers and information inequalities between the academic and the social communities. First, we collected the full text and the metadata of pandemic-related articles and Twitter data mentioning the articles. Second, we extracted and analyzed the topics and sentiment tendencies of the articles and related tweets. Finally, we conducted pandemic-related differential analysis on the academic community and the social community. We mined the resulting data to generate pandemic communication preferences (e.g., information needs, attitude tendencies) of researchers and the public, respectively. The research results from 50,338 articles and 927,266 corresponding tweets mentioning the articles revealed communication differences about global pandemics between the academic and the social communities regarding the consistency of research recognition and the preferences for particular research topics. The analysis of large-scale pandemic-related tweets also confirmed the communication preference differences between the two communities.

Heng Zhang, Chengzhi Zhang

Research on the construction of traditional information science methodology taxonomy is mostly conducted manually. From the limited corpus, researchers have attempted to summarize some of the research methodology entities into several abstract levels (generally three levels); however, they have been unable to provide a more granular hierarchy. Moreover, updating the methodology taxonomy is traditionally a slow process. In this study, we collected full-text academic papers related to information science. First, we constructed a basic methodology taxonomy with three levels by manual annotation. Then, the word vectors of the research methodology entities were trained using the full-text data. Accordingly, the research methodology entities were clustered and the basic methodology taxonomy was expanded using the clustering results to obtain a methodology taxonomy with more levels. This study provides new concepts for constructing a methodology taxonomy of information science. The proposed methodology taxonomy is semi-automated; it is more detailed than conventional schemes and the speed of taxonomy renewal has been enhanced.

Chengzhi Zhang, Lifan Liu, Yuzhuo Wang

Multidisciplinary cooperation is now common in research since social issues inevitably involve multiple disciplines. In research articles, reference information, especially citation content, is an important representation of communication among different disciplines. Analyzing the distribution characteristics of references from different disciplines in research articles is basic to detecting the sources of referred information and identifying contributions of different disciplines. This work takes articles in PLoS as the data and characterizes the references from different disciplines based on Citation Content Analysis (CCA). First, we download 210,334 full-text articles from PLoS and collect the information of the in-text citations. Then, we identify the discipline of each reference in these academic articles. To characterize the distribution of these references, we analyze three characteristics, namely, the number of citations, the average cited intensity and the average citation length. Finally, we conclude that the distributions of references from different disciplines are significantly different. Although most references come from Natural Science, Humanities and Social Sciences play important roles in the Introduction and Background sections of the articles. Basic disciplines, such as Mathematics, mainly provide research methods in the articles in PLoS. Citations mentioned in the Results and Discussion sections of articles are mainly in-discipline citations, such as citations from Nursing and Medicine in PLoS.

Shutian Ma, Heng Zhang, Chengzhi Zhang et al.

Citation recommendation is an important task to assist scholars in finding candidate literature to cite. Traditional studies focus on static models of recommending citations, which do not explicitly distinguish differences between papers that are caused by temporal variations. Although, some researchers have investigated chronological citation recommendation by adding time related function or modeling textual topics dynamically. These solutions can hardly cope with function generalization or cold-start problems when there is no information for user profiling or there are isolated papers never being cited. With the rise and fall of science paradigms, scientific topics tend to change and evolve over time. People would have the time preference when citing papers, since most of the theoretical basis exist in classical readings that published in old time, while new techniques are proposed in more recent papers. To explore chronological citation recommendation, this paper wants to predict the time preference based on user queries, which is a probability distribution of citing papers published in different time slices. Then, we use this time preference to re-rank the initial citation list obtained by content-based filtering. Experimental results demonstrate that task performance can be further enhanced by time preference and it's flexible to be added in other citation recommendation frameworks.

Yuzhuo Wang, Chengzhi Zhang

In the era of big data, the advancement, improvement, and application of algorithms in academic research have played an important role in promoting the development of different disciplines. Academic papers in various disciplines, especially computer science, contain a large number of algorithms. Identifying the algorithms from the full-text content of papers can determine popular or classical algorithms in a specific field and help scholars gain a comprehensive understanding of the algorithms and even the field. To this end, this article takes the field of natural language processing (NLP) as an example and identifies algorithms from academic papers in the field. A dictionary of algorithms is constructed by manually annotating the contents of papers, and sentences containing algorithms in the dictionary are extracted through dictionary-based matching. The number of articles mentioning an algorithm is used as an indicator to analyze the influence of that algorithm. Our results reveal the algorithm with the highest influence in NLP papers and show that classification algorithms represent the largest proportion among the high-impact algorithms. In addition, the evolution of the influence of algorithms reflects the changes in research tasks and topics in the field, and the changes in the influence of different algorithms show different trends. As a preliminary exploration, this paper conducts an analysis of the impact of algorithms mentioned in the academic text, and the results can be used as training data for the automatic extraction of large-scale algorithms in the future. The methodology in this paper is domain-independent and can be applied to other domains.

Marcus Kalander, Min Zhou, Chengzhi Zhang et al.

Telecommunication networks play a critical role in modern society. With the arrival of 5G networks, these systems are becoming even more diversified, integrated, and intelligent. Traffic forecasting is one of the key components in such a system, however, it is particularly challenging due to the complex spatial-temporal dependency. In this work, we consider this problem from the aspect of a cellular network and the interactions among its base stations. We thoroughly investigate the characteristics of cellular network traffic and shed light on the dependency complexities based on data collected from a densely populated metropolis area. Specifically, we observe that the traffic shows both dynamic and static spatial dependencies as well as diverse cyclic temporal patterns. To address these complexities, we propose an effective deep-learning-based approach, namely, Spatio-Temporal Hybrid Graph Convolutional Network (STHGCN). It employs GRUs to model the temporal dependency, while capturing the complex spatial dependency through a hybrid-GCN from three perspectives: spatial proximity, functional similarity, and recent trend similarity. We conduct extensive experiments on real-world traffic datasets collected from telecommunication networks. Our experimental results demonstrate the superiority of the proposed model in that it consistently outperforms both classical methods and state-of-the-art deep learning models, while being more robust and stable.

Chao Lu, Yi Bu, Xianlei Dong et al.

The number of publications and the number of citations received have become the most common indicators of scholarly success. In this context, scientific writing increasingly plays an important role in scholars' scientific careers. To understand the relationship between scientific writing and scientific impact, this paper selected 12 variables of linguistic complexity as a proxy for depicting scientific writing. We then analyzed these features from 36,400 full-text Biology articles and 1,797 full-text Psychology articles. These features were compared to the scientific impact of articles, grouped into high, medium, and low categories. The results suggested no practical significant relationship between linguistic complexity and citation strata in either discipline. This suggests that textual complexity plays little role in scientific impact in our data sets.

Chao Lu, Yi Bu, Jie Wang et al.

Publishing articles in high-impact English journals is difficult for scholars around the world, especially for non-native English-speaking scholars (NNESs), most of whom struggle with proficiency in English. In order to uncover the differences in English scientific writing between native English-speaking scholars (NESs) and NNESs, we collected a large-scale data set containing more than 150,000 full-text articles published in PLoS between 2006 and 2015. We divided these articles into three groups according to the ethnic backgrounds of the first and corresponding authors, obtained by Ethnea, and examined the scientific writing styles in English from a two-fold perspective of linguistic complexity: (1) syntactic complexity, including measurements of sentence length and sentence complexity; and (2) lexical complexity, including measurements of lexical diversity, lexical density, and lexical sophistication. The observations suggest marginal differences between groups in syntactical and lexical complexity.

Qingqing Zhou, Chengzhi Zhang, Star X. Zhao et al.

As with articles and journals, the customary methods for measuring books' academic impact mainly involve citations, which is easy but limited to interrogating traditional citation databases and scholarly book reviews, Researchers have attempted to use other metrics, such as Google Books, libcitation, and publisher prestige. However, these approaches lack content-level information and cannot determine the citation intentions of users. Meanwhile, the abundant online review resources concerning academic books can be used to mine deeper information and content utilizing altmetric perspectives. In this study, we measure the impacts of academic books by multi-granularity mining online reviews, and we identify factors that affect a book's impact. First, online reviews of a sample of academic books on Amazon.cn are crawled and processed. Then, multi-granularity review mining is conducted to identify review sentiment polarities and aspects' sentiment values. Lastly, the numbers of positive reviews and negative reviews, aspect sentiment values, star values, and information regarding helpfulness are integrated via the entropy method, and lead to the calculation of the final book impact scores. The results of a correlation analysis of book impact scores obtained via our method versus traditional book citations show that, although there are substantial differences between subject areas, online book reviews tend to reflect the academic impact. Thus, we infer that online reviews represent a promising source for mining book impact within the altmetric perspective and at the multi-granularity content level. Moreover, our proposed method might also be a means by which to measure other books besides academic publications.

Qingqing Zhou, Rui Xia, Chengzhi Zhang

With the development of e-commerce, many products are now being sold worldwide, and manufacturers are eager to obtain a better understanding of customer behavior in various regions. To achieve this goal, most previous efforts have focused mainly on questionnaires, which are time-consuming and costly. The tremendous volume of product reviews on e-commerce websites has seen a new trend emerge, whereby manufacturers attempt to understand user preferences by analyzing online reviews. Following this trend, this paper addresses the problem of studying customer behavior by exploiting recently developed opinion mining techniques. This work is novel for three reasons. First, questionnaire-based investigation is automatically enabled by employing algorithms for template-based question generation and opinion mining-based answer extraction. Using this system, manufacturers are able to obtain reports of customer behavior featuring a much larger sample size, more direct information, a higher degree of automation, and a lower cost. Second, international customer behavior study is made easier by integrating tools for multilingual opinion mining. Third, this is the first time an automatic questionnaire investigation has been conducted to compare customer behavior in China and America, where product reviews are written and read in Chinese and English, respectively. Our study on digital cameras, smartphones, and tablet computers yields three findings. First, Chinese customers follow the Doctrine of the Mean, and often use euphemistic expressions, while American customers express their opinions more directly. Second, Chinese customers care more about general feelings, while American customers pay more attention to product details. Third, Chinese customers focus on external features, while American customers care more about the internal features of products.

Chengzhi Zhang, Dan Wu

Purpose: Terminology is the set of technical words or expressions used in specific contexts, which denotes the core concept in a formal discipline and is usually applied in the fields of machine translation, information retrieval, information extraction and text categorization, etc. Bilingual terminology extraction plays an important role in the application of bilingual dictionary compilation, bilingual Ontology construction, machine translation and cross-language information retrieval etc. This paper addresses the issues of monolingual terminology extraction and bilingual term alignment based on multi-level termhood. Design/methodology/approach: A method based on multi-level termhood is proposed. The new method computes the termhood of the terminology candidate as well as the sentence that includes the terminology by the comparison of the corpus. Since terminologies and general words usually have differently distribution in the corpus, termhood can also be used to constrain and enhance the performance of term alignment when aligning bilingual terms on the parallel corpus. In this paper, bilingual term alignment based on termhood constraints is presented. Findings: Experiment results show multi-level termhood can get better performance than existing method for terminology extraction. If termhood is used as constrain factor, the performance of bilingual term alignment can be improved.

Sa Liu, Chengzhi Zhang

Cross-Language Information Retrieval (CLIR) and machine translation (MT) resources, such as dictionaries and parallel corpora, are scarce and hard to come by for special domains. Besides, these resources are just limited to a few languages, such as English, French, and Spanish and so on. So, obtaining comparable corpora automatically for such domains could be an answer to this problem effectively. Comparable corpora, that the subcorpora are not translations of each other, can be easily obtained from web. Therefore, building and using comparable corpora is often a more feasible option in multilingual information processing. Comparability metrics is one of key issues in the field of building and using comparable corpus. Currently, there is no widely accepted definition or metrics method of corpus comparability. In fact, Different definitions or metrics methods of comparability might be given to suit various tasks about natural language processing. A new comparability, namely, termhood-based metrics, oriented to the task of bilingual terminology extraction, is proposed in this paper. In this method, words are ranked by termhood not frequency, and then the cosine similarities, calculated based on the ranking lists of word termhood, is used as comparability. Experiments results show that termhood-based metrics performs better than traditional frequency-based metrics.