Ye Yang

Jinxiang Meng, Shaoping Huang, Fangyu Lei et al.

Real-world data visualization (DV) requires native environmental grounding, cross-platform evolution, and proactive intent alignment. Yet, existing benchmarks often suffer from code-sandbox confinement, single-language creation-only tasks, and assumption of perfect intent. To bridge these gaps, we introduce DV-World, a benchmark of 260 tasks designed to evaluate DV agents across real-world professional lifecycles. DV-World spans three domains: DV-Sheet for native spreadsheet manipulation including chart and dashboard creation as well as diagnostic repair; DV-Evolution for adapting and restructuring reference visual artifacts to fit new data across diverse programming paradigms and DV-Interact for proactive intent alignment with a user simulator that mimics real-world ambiguous requirements. Our hybrid evaluation framework integrates Table-value Alignment for numerical precision and MLLM-as-a-Judge with rubrics for semantic-visual assessment. Experiments reveal that state-of-the-art models achieve less than 50% overall performance, exposing critical deficits in handling the complex challenges of real-world data visualization. DV-World provides a realistic testbed to steer development toward the versatile expertise required in enterprise workflows. Our data and code are available at \href{https://github.com/DA-Open/DV-World}{this project page}.

Yuekai Huang, Ye Yang, Junjie Wang et al.

In open source software (OSS) communities, existing leadership indicators are dominantly measured by code contribution or community influence. Recent studies on emergent leadership shed light on additional dimensions such as intellectual stimulation in collaborative communications. To that end, this paper proposes an automated approach, named iLead, to mine communication styles and identify emergent leadership behaviors in OSS communities, using issue comments data. We start with the construction of 6 categories of leadership behaviors based on existing leadership studies. Then, we manually label leadership behaviors in 10,000 issue comments from 10 OSS projects, and extract 304 heuristic linguistic patterns which represent different types of emergent leadership behaviors in flexible and concise manners. Next, an automated algorithm is developed to merge and consolidate different pattern sets extracted from multiple projects into a final pattern ranking list, which can be applied for the automatic leadership identification. The evaluation results show that iLead can achieve a median precision of 0.82 and recall of 0.78, outperforming ten machine/deep learning baselines. To demonstrate practical usefulness, we also conduct empirical analysis and human evaluation of the identified leadership behaviors from iLead. We argue that emergent leadership behaviors in issue discussion should be taken into consideration to broaden existing OSS leadership viewpoints. Practical insights on community building and leadership skill development are offered for OSS community and individual developers, respectively.

Lin Shi, Ziyou Jiang, Ye Yang et al.

Collaborative live chats are gaining popularity as a development communication tool. In community live chatting, developers are likely to post issues they encountered (e.g., setup issues and compile issues), and other developers respond with possible solutions. Therefore, community live chats contain rich sets of information for reported issues and their corresponding solutions, which can be quite useful for knowledge sharing and future reuse if extracted and restored in time. However, it remains challenging to accurately mine such knowledge due to the noisy nature of interleaved dialogs in live chat data. In this paper, we first formulate the problem of issue-solution pair extraction from developer live chat data, and propose an automated approach, named ISPY, based on natural language processing and deep learning techniques with customized enhancements, to address the problem. Specifically, ISPY automates three tasks: 1) Disentangle live chat logs, employing a feedforward neural network to disentangle a conversation history into separate dialogs automatically; 2) Detect dialogs discussing issues, using a novel convolutional neural network (CNN), which consists of a BERT-based utterance embedding layer, a context-aware dialog embedding layer, and an output layer; 3) Extract appropriate utterances and combine them as corresponding solutions, based on the same CNN structure but with different feeding inputs. To evaluate ISPY, we compare it with six baselines, utilizing a dataset with 750 dialogs including 171 issue-solution pairs and evaluate ISPY from eight open source communities. The results show that, for issue-detection, our approach achieves the F1 of 76%, and outperforms all baselines by 30%. Our approach achieves the F1 of 63% for solution-extraction and outperforms the baselines by 20%.

Lin Shi, Xiao Chen, Ye Yang et al.

Modern communication platforms such as Gitter and Slack play an increasingly critical role in supporting software teamwork, especially in open source development.Conversations on such platforms often contain intensive, valuable information that may be used for better understanding OSS developer communication and collaboration. However, little work has been done in this regard. To bridge the gap, this paper reports a first comprehensive empirical study on developers' live chat, investigating when they interact, what community structures look like, which topics are discussed, and how they interact. We manually analyze 749 dialogs in the first phase, followed by an automated analysis of over 173K dialogs in the second phase. We find that developers tend to converse more often on weekdays, especially on Wednesdays and Thursdays (UTC), that there are three common community structures observed, that developers tend to discuss topics such as API usages and errors, and that six dialog interaction patterns are identified in the live chat communities. Based on the findings, we provide recommendations for individual developers and OSS communities, highlight desired features for platform vendors, and shed light on future research directions. We believe that the findings and insights will enable a better understanding of developers' live chat, pave the way for other researchers, as well as a better utilization and mining of knowledge embedded in the massive chat history.

Jiaheng Li, Donghe Li, Ye Yang et al.

The growing penetration of renewable energy sources in power systems has increased the complexity and uncertainty of load forecasting, especially for integrated energy systems with multiple energy carriers. Traditional forecasting methods heavily rely on historical data and exhibit limited transferability across different scenarios, posing significant challenges for emerging applications in smart grids and energy internet. This paper proposes the TSLLM-Load Forecasting Mechanism, a novel zero-shot load forecasting framework based on large language models (LLMs) to address these challenges. The framework consists of three key components: a data preprocessing module that handles multi-source energy load data, a time series prompt generation module that bridges the semantic gap between energy data and LLMs through multi-task learning and similarity alignment, and a prediction module that leverages pre-trained LLMs for accurate forecasting. The framework's effectiveness was validated on a real-world dataset comprising load profiles from 20 Australian solar-powered households, demonstrating superior performance in both conventional and zero-shot scenarios. In conventional testing, our method achieved a Mean Squared Error (MSE) of 0.4163 and a Mean Absolute Error (MAE) of 0.3760, outperforming existing approaches by at least 8\%. In zero-shot prediction experiments across 19 households, the framework maintained consistent accuracy with a total MSE of 11.2712 and MAE of 7.6709, showing at least 12\% improvement over current methods. The results validate the framework's potential for accurate and transferable load forecasting in integrated energy systems, particularly beneficial for renewable energy integration and smart grid applications.

Ye Yang, Xue Xiao, Ping Yin et al.

API calls by large language models (LLMs) offer a cutting-edge approach for data analysis. However, their ability to effectively utilize tools via API calls remains underexplored in knowledge-intensive domains like meteorology. This paper introduces KG2data, a system that integrates knowledge graphs, LLMs, ReAct agents, and tool-use technologies to enable intelligent data acquisition and query handling in the meteorological field. Using a virtual API, we evaluate API call accuracy across three metrics: name recognition failure, hallucination failure, and call correctness. KG2data achieves superior performance (1.43%, 0%, 88.57%) compared to RAG2data (16%, 10%, 72.14%) and chat2data (7.14%, 8.57%, 71.43%). KG2data differs from typical LLM-based systems by addressing their limited access to domain-specific knowledge, which hampers performance on complex or terminology-rich queries. By using a knowledge graph as persistent memory, our system enhances content retrieval, complex query handling, domain-specific reasoning, semantic relationship resolution, and heterogeneous data integration. It also mitigates the high cost of fine-tuning LLMs, making the system more adaptable to evolving domain knowledge and API structures. In summary, KG2data provides a novel solution for intelligent, knowledge-based question answering and data analysis in domains with high knowledge demands.

Gengxian Cao, Fengyuan Li, Hong Duan et al.

This paper introduces a novel multi-Agent framework that automates the end to end production of Qinqiang opera by integrating Large Language Models , visual generation, and Text to Speech synthesis. Three specialized agents collaborate in sequence: Agent1 uses an LLM to craft coherent, culturally grounded scripts;Agent2 employs visual generation models to render contextually accurate stage scenes; and Agent3 leverages TTS to produce synchronized, emotionally expressive vocal performances. In a case study on Dou E Yuan, the system achieved expert ratings of 3.8 for script fidelity, 3.5 for visual coherence, and 3.8 for speech accuracy-culminating in an overall score of 3.6, a 0.3 point improvement over a Single Agent baseline. Ablation experiments demonstrate that removing Agent2 or Agent3 leads to drops of 0.4 and 0.5 points, respectively, underscoring the value of modular collaboration. This work showcases how AI driven pipelines can streamline and scale the preservation of traditional performing arts, and points toward future enhancements in cross modal alignment, richer emotional nuance, and support for additional opera genres.

Razieh Saremi, Hamid Shamszare, Marzieh Lotfalian Saremi et al.

Software crowdsourcing platforms employ extrinsic rewards such as rating or ranking systems to motivate workers. Such rating systems are noisy and provide limited knowledge about workers' preferences and performance. To develop better understanding of worker reliability and trustworthiness in software crowdsourcing, this paper reports an empirical study conducted on more than one year's real-world data from TopCoder, one of the leading software crowdsourcing platforms. To do so, first, we create a bipartite network of active workers based on common task registrations. Then, we use the Clauset-Newman-Moore graph clustering algorithm to identify worker clusters in the network. Finally, we conduct an empirical evaluation to measure and analyze workers' behavior per identified community in the platform by workers' rating. More specifically, workers' behavior is analyzed based on their performances in terms of reliability, trustworthiness, and success; their preferences in terms of efficiency and elasticity; and strategies in terms of comfort, confidence, and deceitfulness. The main result of this study identified four communities of active workers: mixed-ranked, high-ranked, mid-ranked, and low-ranked. This study shows that the low-ranked community associates with the highest reliable workers with an average reliability of 25%, while the mixed-ranked community contains the most trustworthy workers with average trustworthiness of 16%. Such empirical evidence is beneficial to help exploring resourcing options while understanding the relations among unknown resources to improve task success.

Razieh Saremi, Hardik Yagnik, Julian Togelius et al.

The complexity of software tasks and the uncertainty of crowd developer behaviors make it challenging to plan crowdsourced software development (CSD) projects. In a competitive crowdsourcing marketplace, competition for shared worker resources from multiple simultaneously open tasks adds another layer of uncertainty to the potential outcomes of software crowdsourcing. These factors lead to the need for supporting CSD managers with automated scheduling to improve the visibility and predictability of crowdsourcing processes and outcomes. To that end, this paper proposes an evolutionary algorithm-based task scheduling method for crowdsourced software development. The proposed evolutionary scheduling method uses a multiobjective genetic algorithm to recommend an optimal task start date. The method uses three fitness functions, based on project duration, task similarity, and task failure prediction, respectively. The task failure fitness function uses a neural network to predict the probability of task failure with respect to a specific task start date. The proposed method then recommends the best tasks start dates for the project as a whole and each individual task so as to achieve the lowest project failure ratio. Experimental results on 4 projects demonstrate that the proposed method has the potential to reduce project duration by a factor of 33-78%.

Razieh Saremi, Ye Yang, Gregg Vesonder et al.

A typical crowdsourcing software development(CSD) marketplace consists of a list of software tasks as service demands and a pool of freelancer developers as service suppliers. Highly dynamic and competitive CSD market places may result in task failure due to unforeseen risks, such as increased competition over shared worker supply, or uncertainty associated with workers' experience and skills, and so on. To improve CSD effectiveness, it is essential to better understand and plan with respect to dynamic worker characteristics and risks associated with CSD processes. In this paper, we present a hybrid simulation model, CrowdSim, to forecast crowdsourcing task failure risk in competitive CSD platforms. CrowdSim is composed of three layered components: the macro-level reflects the overall crowdsourcing platform based on system dynamics,the meso-level represents the task life cycle based on discrete event simulation, and the micro-level models the crowd workers' decision-making processes based on agent-based simulation. CrowdSim is evaluated through three CSD decision scenarios to demonstrate its effectiveness, using a real-world historical dataset and the results demonstrate CrowdSim's potential in empowering crowdsourcing managers to explore crowdsourcing outcomes with respect to different task scheduling options.

Denisse Martinez Mejorado, Razieh Saremi, Ye Yang et al.

Context: The success of software crowdsourcing depends on steady tasks supply and active worker pool. Existing analysis reveals an average task failure ratio of 15.7% in software crowdsourcing market. Goal: The objective of this study is to empirically investigate patterns and effect of task diversity in software crowdsourcing platform in order to improve the success and efficiency of software crowdsourcing. Method: We propose a conceptual task diversity model, and develop an approach to measuring and analyzing task diversity.More specifically, this includes grouping similar tasks, ranking them based on their competition level and identifying the dominant attributes that distinguish among these levels, and then studying the impact of task diversity on task success and worker performance in crowdsourcing platform. The empirical study is conducted on more than one year's real-world data from TopCoder, the leading software crowdsourcing platform. Results: We identified that monetary prize and task complexity are the dominant attributes that differentiate among different competition levels. Based on these dominant attributes, we found three task diversity patterns (configurations) from workers behavior perspective: responsive to prize, responsive to prize and complexity and over responsive to prize. This study supports that1) responsive to prize configuration provides highest level of task density and workers' reliability in a platform; 2) responsive to prize and complexity configuration leads to attracting high level of trustworthy workers; 3) over responsive to prize configuration results in highest task stability and the lowest failure ratio in the platform for not high similar tasks.

Sascha Wirges, Ye Yang, Sven Richter et al.

We propose an object detector for top-view grid maps which is additionally trained to generate an enriched version of its input. Our goal in the joint model is to improve generalization by regularizing towards structural knowledge in form of a map fused from multiple adjacent range sensor measurements. This training data can be generated in an automatic fashion, thus does not require manual annotations. We present an evidential framework to generate training data, investigate different model architectures and show that predicting enriched inputs as an additional task can improve object detection performance.

Junjie Wang, Ye Yang, Zhe Yu et al.

Trade-offs such as "how much testing is enough" are critical yet challenging project decisions in software engineering. Most existing approaches adopt risk-driven or value-based analysis to prioritize test cases and minimize test runs. However, none of these is applicable to the emerging crowd testing paradigm where task requesters typically have no control over online crowdworkers's dynamic behavior and uncertain performance. In current practice, deciding when to close a crowdtesting task is largely done by guesswork due to lack of decision support. This paper intends to fill this gap by introducing automated decision support for monitoring and determining appropriate time to close the crowdtesting tasks. First, this paper investigates the necessity and feasibility of close prediction of crowdtesting tasks based on industrial dataset. Then,it designs 8 methods for close prediction, based on various models including the bug trend, bug arrival model, capture-recapture model.Finally, the evaluation is conducted on 218 crowdtesting tasks from one of the largest crowdtesting platforms in China, and the results show that a median of 91% bugs can be detected with 49% saved cost.

Junjie Wang, Ye Yang, Rahul Krishna et al.

Crowdtesting has grown to be an effective alter-native to traditional testing, especially in mobile apps. However,crowdtesting is hard to manage in nature. Given the complexity of mobile applications and unpredictability of distributed, parallel crowdtesting process, it is difficult to estimate (a) the remaining number of bugs as yet undetected or (b) the required cost to find those bugs. Experience-based decisions may result in ineffective crowdtesting process. This paper aims at exploring automated decision support to effectively manage crowdtesting process. The proposed ISENSE applies incremental sampling technique to process crowdtesting reports arriving in chronological order, organizes them into fixed-size groups as dynamic inputs, and predicts two test completion indicators in an incrementally manner. The two indicators are: 1)total number of bugs predicted with Capture-ReCapture (CRC)model, and 2) required test cost for achieving certain test objectives predicted with AutoRegressive Integrated Moving Average(ARIMA) model. We assess ISENSE using 46,434 reports of 218 crowdtesting tasks from one of the largest crowdtesting platforms in China. Its effectiveness is demonstrated through two applications for automating crowdtesting management, i.e. automation oftask closing decision, and semi-automation of task closing trade-off analysis. The results show that decision automation using ISENSE will provide managers with greater opportunities to achieve cost-effectiveness gains of crowdtesting. Specifically, a median of 100% bugs can be detected with 30% saved cost basedon the automated close prediction

Muhammad Rezaul Karim, David Messinger, Ye Yang et al.

Crowdsourced software development (CSD) offers a series of specified tasks to a large crowd of trustworthy software workers. Topcoder is a leading platform to manage the whole process of CSD. While increasingly accepted as a realistic option for software development, preliminary analysis on Topcoder's software crowd worker behaviors reveals an alarming task-quitting rate of 82.9%. In addition, a substantial number of tasks do not receive any successful submission. In this paper, we report about a methodology to improve the efficiency of CSD. We apply massive data analytics and machine leaning to (i) perform comparative analysis on alternative technique analysis to predict likelihood of winners and quitters for each task, (ii) significantly reduce the amount of non-succeeding development effort in registered but inappropriate tasks, (iii) identify and rank the most qualified registered workers for each task, and (iv) provide reliable prediction of tasks risky to get any successful submission. Our results and analysis show that Random Forest (RF) based predictive technique performs best among the alternative techniques studied. Applying RF, the tasks recommended to workers can reduce the amount of non-succeeding development effort to a great extent. On average, over a period of 30 days, the savings are 3.5 and 4.6 person-days per registered tasks for experienced resp. unexperienced workers. For the task-related recommendations of workers, we can accurately recommend at least 1 actual winner in the top ranked workers, particularly 94.07% of the time among the top-2 recommended workers for each task. Finally, we can predict, with more than 80% F-measure, the tasks likely not getting any submission, thus triggering timely corrective actions from CSD platforms or task requesters.

Yueming Sun, Ye Yang, He Zhang et al.

[Background]: Systematic Literature Review (SLR) has become an important software engineering research method but costs tremendous efforts. [Aim]: This paper proposes an approach to leverage on empirically evolved ontology to support automating key SLR activities. [Method]: First, we propose an ontology, SLRONT, built on SLR experiences and best practices as a groundwork to capture common terminologies and their relationships during SLR processes; second, we present an extended version of SLRONT, the COSONT and instantiate it with the knowledge and concepts extracted from structured abstracts. Case studies illustrate the details of applying it for supporting SLR steps. [Results]: Results show that through using COSONT, we acquire the same conclusion compared with sheer manual works, but the efforts involved is significantly reduced. [Conclusions]: The approach of using ontology could effectively and efficiently support the conducting of systematic literature review.

Tim Menzies, Ye Yang, George Mathew et al.

Context:More than half the literature on software effort estimation (SEE) focuses on comparisons of new estimation methods. Surprisingly, there are no studies comparing state of the art latest methods with decades-old approaches. Objective:To check if new SEE methods generated better estimates than older methods. Method: Firstly, collect effort estimation methods ranging from "classical" COCOMO (parametric estimation over a pre-determined set of attributes) to "modern" (reasoning via analogy using spectral-based clustering plus instance and feature selection, and a recent "baseline method" proposed in ACM Transactions on Software Engineering).Secondly, catalog the list of objections that lead to the development of post-COCOMO estimation methods.Thirdly, characterize each of those objections as a comparison between newer and older estimation methods.Fourthly, using four COCOMO-style data sets (from 1991, 2000, 2005, 2010) and run those comparisons experiments.Fifthly, compare the performance of the different estimators using a Scott-Knott procedure using (i) the A12 effect size to rule out "small" differences and (ii) a 99% confident bootstrap procedure to check for statistically different groupings of treatments). Results: The major negative results of this paper are that for the COCOMO data sets, nothing we studied did any better than Boehm's original procedure. Conclusions: When COCOMO-style attributes are available, we strongly recommend (i) using that data and (ii) use COCOMO to generate predictions. We say this since the experiments of this paper show that, at least for effort estimation,how data is collected is more important than what learner is applied to that data.

Zheng Li, Liam O'Brien, Ye Yang

[Background:] Software effort prediction methods and models typically assume positive correlation between software product complexity and development effort. However, conflicting observations, i.e. negative correlation between product complexity and actual effort, have been witnessed from our experience with the COCOMO81 dataset. [Aim:] Given our doubt about whether the observed phenomenon is a coincidence, this study tries to investigate if an increase in product complexity can result in the abovementioned counter-intuitive trend in software development projects. [Method:] A modified association rule mining approach is applied to the transformed COCOMO81 dataset. To reduce noise of analysis, this approach uses a constant antecedent (Complexity increases while Effort decreases) to mine potential consequents with pruning. [Results:] The experiment has respectively mined four, five, and seven association rules from the general, embedded, and organic projects data. The consequents of the mined rules suggested two main aspects, namely human capability and product scale, to be particularly concerned in this study. [Conclusions:] The negative correlation between complexity and effort is not a coincidence under particular conditions. In a software project, interactions between product complexity and other factors, such as Programmer Capability and Analyst Capability, can inevitably play a "friction" role in weakening the practical influences of product complexity on actual development effort.