Thanasis Vergoulis

Paris Koloveas, Serafeim Chatzopoulos, Christos Tryfonopoulos et al.

In the field of Computer Science, conference and workshop papers serve as important contributions, carrying substantial weight in research assessment processes, compared to other disciplines. However, a considerable number of these papers are not assigned a Digital Object Identifier (DOI), hence their citations are not reported in widely used citation datasets like OpenCitations and Crossref, raising limitations to citation analysis. While the Microsoft Academic Graph (MAG) previously addressed this issue by providing substantial coverage, its discontinuation has created a void in available data. BIP! NDR aims to alleviate this issue and enhance the research assessment processes within the field of Computer Science. To accomplish this, it leverages a workflow that identifies and retrieves Open Science papers lacking DOIs from the DBLP Corpus, and by performing text analysis, it extracts citation information directly from their full text. The current version of the dataset contains more than 510K citations made by approximately 60K open access Computer Science conference or workshop papers that, according to DBLP, do not have a DOI.

Serafeim Chatzopoulos, Paris Koloveas, Kleanthis Vichos et al.

Modern researchers engage in diverse activities, assume multiple contribution roles, and produce a variety of outputs beyond traditional publications. This broader view of research contributions is increasingly recognised by responsible research assessment initiatives. However, existing researcher profiling platforms remain largely focused on publications and publication-centric indicators, offering limited support for contextualised and multi-dimensional representations of research careers. This paper presents BIP! Scholar, a platform that supports flexible researcher profiling through a template-driven approach. Researchers can create profiles tailored to different presentation or assessment contexts using track-based, narrative-style, or hybrid templates which support the representation of diverse outputs, contribution roles, and broader research activities. The platform also supports research assessment experts who wish to design and evaluate experimental profile templates.

Paris Koloveas, Serafeim Chatzopoulos, Thanasis Vergoulis et al.

This work investigates the ability of open Large Language Models (LLMs) to predict citation intent through in-context learning and fine-tuning. Unlike traditional approaches relying on domain-specific pre-trained models like SciBERT, we demonstrate that general-purpose LLMs can be adapted to this task with minimal task-specific data. We evaluate twelve model variations across five prominent open LLM families using zero-, one-, few-, and many-shot prompting. Our experimental study identifies the top-performing model and prompting parameters through extensive in-context learning experiments. We then demonstrate the significant impact of task-specific adaptation by fine-tuning this model, achieving a relative F1-score improvement of 8% on the SciCite dataset and 4.3% on the ACL-ARC dataset compared to the instruction-tuned baseline. These findings provide valuable insights for model selection and prompt engineering. Additionally, we make our end-to-end evaluation framework and models openly available for future use.

Paris Koloveas, Serafeim Chatzopoulos, Thanasis Vergoulis et al.

The proliferation of scientific literature presents an increasingly significant challenge for researchers. While Large Language Models (LLMs) offer promise, existing tools often provide verbose summaries that risk replacing, rather than assisting, the reading of the source material. This paper introduces InsightGUIDE, a novel AI-powered tool designed to function as a reading assistant, not a replacement. Our system provides concise, structured insights that act as a "map" to a paper's key elements by embedding an expert's reading methodology directly into its core AI logic. We present the system's architecture, its prompt-driven methodology, and a qualitative case study comparing its output to a general-purpose LLM. The results demonstrate that InsightGUIDE produces more structured and actionable guidance, serving as a more effective tool for the modern researcher.

Paris Koloveas, Serafeim Chatzopoulos, Dionysis Diamantis et al.

The growing volume of scientific literature makes it challenging for scientists to move from a list of papers to a synthesized understanding of a topic. Because of the constant influx of new papers on a daily basis, even if a scientist identifies a promising set of papers, they still face the tedious task of individually reading through dozens of titles and abstracts to make sense of occasionally conflicting findings. To address this critical bottleneck in the research workflow, we introduce a summarization feature to BIP! Finder, a scholarly search engine that ranks literature based on distinct impact aspects like popularity and influence. Our approach enables users to generate two types of summaries from top-ranked search results: a concise summary for an instantaneous at-a-glance comprehension and a more comprehensive literature review-style summary for greater, better-organized comprehension. This ability dynamically leverages BIP! Finder's already existing impact-based ranking and filtering features to generate context-sensitive, synthesized narratives that can significantly accelerate literature discovery and comprehension.

Gavin Farrell, Eleni Adamidi, Rafael Andrade Buono et al.

Artificial intelligence (AI) has recently seen transformative breakthroughs in the life sciences, expanding possibilities for researchers to interpret biological information at an unprecedented capacity, with novel applications and advances being made almost daily. In order to maximise return on the growing investments in AI-based life science research and accelerate this progress, it has become urgent to address the exacerbation of long-standing research challenges arising from the rapid adoption of AI methods. We review the increased erosion of trust in AI research outputs, driven by the issues of poor reusability and reproducibility, and highlight their consequent impact on environmental sustainability. Furthermore, we discuss the fragmented components of the AI ecosystem and lack of guiding pathways to best support Open and Sustainable AI (OSAI) model development. In response, this perspective introduces a practical set of OSAI recommendations directly mapped to over 300 components of the AI ecosystem. Our work connects researchers with relevant AI resources, facilitating the implementation of sustainable, reusable and transparent AI. Built upon life science community consensus and aligned to existing efforts, the outputs of this perspective are designed to aid the future development of policy and structured pathways for guiding AI implementation.

Serafeim Chatzopoulos, Thanasis Vergoulis, Dimitrios Skoutas et al.

Heterogeneous information networks (HINs) represent different types of entities and relationships between them. Exploring, analysing, and extracting knowledge from such networks relies on metapath queries that identify pairs of entities connected by relationships of diverse semantics. While the real-time evaluation of metapath query workloads on large, web-scale HINs is highly demanding in computational cost, current approaches do not exploit interrelationships among the queries. In this paper, we present ATRAPOS, a new approach for the real-time evaluation of metapath query workloads that leverages a combination of efficient sparse matrix multiplication and intermediate result caching. ATRAPOS selects intermediate results to cache and reuse by detecting frequent sub-metapaths among workload queries in real time, using a tailor-made data structure, the Overlap Tree, and an associated caching policy. Our experimental study on real data shows that ATRAPOS accelerates exploratory data analysis and mining on HINs, outperforming off-the-shelf caching approaches and state-of-the-art research prototypes in all examined scenarios. -- Note that this version of our work is more extended than the one presented in TheWebConf 2023 (doi: 10.1145/3543507.3583322)

Thanasis Vergoulis, Ilias Kanellos, Claudio Atzori et al.

The growth rate of the number of scientific publications is constantly increasing, creating important challenges in the identification of valuable research and in various scholarly data management applications, in general. In this context, measures which can effectively quantify the scientific impact could be invaluable. In this work, we present BIP! DB, an open dataset that contains a variety of impact measures calculated for a large collection of more than 100 million scientific publications from various disciplines.

Thanasis Vergoulis, Ilias Kanellos, Giorgos Giannopoulos et al.

Estimating the expected impact of an article is valuable for various applications (e.g., article/cooperator recommendation). Most existing approaches attempt to predict the exact number of citations each article will receive in the near future, however this is a difficult regression analysis problem. Moreover, most approaches rely on the existence of rich metadata for each article, a requirement that cannot be adequately fulfilled for a large number of them. In this work, we take advantage of the fact that solving a simpler machine learning problem, that of classifying articles based on their expected impact, is adequate for many real world applications and we propose a simplified model that can be trained using minimal article metadata. Finally, we examine various configurations of this model and evaluate their effectiveness in solving the aforementioned classification problem.

Ilias Kanellos, Thanasis Vergoulis, Dimitris Sacharidis et al.

The constantly increasing rate at which scientific papers are published makes it difficult for researchers to identify papers that currently impact the research field of their interest. Hence, approaches to effectively identify papers of high impact have attracted great attention in the past. In this work, we present a method that seeks to rank papers based on their estimated short-term impact, as measured by the number of citations received in the near future. Similar to previous work, our method models a researcher as she explores the paper citation network. The key aspect is that we incorporate an attention-based mechanism, akin to a time-restricted version of preferential attachment, to explicitly capture a researcher's preference to read papers which received a lot of attention recently. A detailed experimental evaluation on four real citation datasets across disciplines, shows that our approach is more effective than previous work in ranking papers based on their short-term impact.