Mohammed R. Anany, Heba Hussien, Sherif G. Aly et al. · 2019
The Software developer productivity is an important indicator that has attracted the attention of the industry over the years. It has been established that improving software productivity enhances the performance of organizations. Despite its importance, a full understanding of contextual factors and how they influence productivity is not attained. One such important factor is the developer’s emotions. In this paper, we conduct an experiment on 11 participants where they attempt to solve 10 ACM-style problems as we monitor their emotions and behaviour in the background. The experiments performed achieve an accuracy of 55.4% on the test set using a random forest classifier. There is room for multiple improvements such as increasing dataset size, performing class balancing, and utilizing different aggregation methods for the data. This paper opens a different track for experimentation relating to the relationship between emotions and software productivity. Achieving a better understanding of this relationship can aid further research that would utilize it to build context aware and pervasive systems that can automatically react to developers’ emotions when going through a low productivity phase and orient them towards emotions that are correlated with positive productivity.
Cited by 4Open access
Akhila Sri Manasa Venigalla, Sridhar Chimalakonda · arXiv (Cornell University) · 2021
The availability of open-source projects facilitates developers to contribute and collaborate on a wide range of projects. As a result, the developer community contributing to such open-source projects is also increasing. Many of the projects involve frequent updates and extensive reuses. A well-updated documentation helps in a better understanding of the software project and also facilitates efficient contribution and reuse. Though software documentation plays an important role in the development and maintenance of software, it also suffers from various issues that include insufficiency, inconsistency, ill-maintainability, and so on. Exploring the perception of developers towards documentation could help in understanding the reasons behind prevalent issues in software documentation. It could further aid in deciding on training that could be given to the developer community towards building more sustainable projects for society. Analyzing sentiments of contributors to a project could provide insights on understanding developer perceptions. Hence, as the first step towards this direction, we analyze sentiments of commit messages specific to the documentation of a software project. To this end, we considered the commit history of 998 GitHub projects from the GHTorrent dataset and identified 10,996 commits that correspond to the documentation of repositories. Further, we apply sentiment analysis techniques to obtain insights on the type of sentiment being expressed in commit messages of the selected commits. We observe that around 45% of the identified commit messages express trust emotion.
Cited by 4Open access
Akhila Sri Manasa Venigalla · Zenodo (CERN European Organization for Nuclear Research) · 2021
First release of documentation-related commit messages dataset, and results of sentiment analysis of these messages.
Cited by 0Open access
Akhila Sri Manasa Venigalla, Sridhar Chimalakonda · arXiv (Cornell University) · 2021
The availability of open-source projects facilitates developers to contribute\nand collaborate on a wide range of projects. As a result, the developer\ncommunity contributing to such open-source projects is also increasing. Many of\nthe projects involve frequent updates and extensive reuses. A well-updated\ndocumentation helps in a better understanding of the software project and also\nfacilitates efficient contribution and reuse. Though software documentation\nplays an important role in the development and maintenance of software, it also\nsuffers from various issues that include insufficiency, inconsistency,\nill-maintainability, and so on. Exploring the perception of developers towards\ndocumentation could help in understanding the reasons behind prevalent issues\nin software documentation. It could further aid in deciding on training that\ncould be given to the developer community towards building more sustainable\nprojects for society. Analyzing sentiments of contributors to a project could\nprovide insights on understanding developer perceptions. Hence, as the first\nstep towards this direction, we analyze sentiments of commit messages specific\nto the documentation of a software project. To this end, we considered the\ncommit history of 998 GitHub projects from the GHTorrent dataset and identified\n10,996 commits that correspond to the documentation of repositories. Further,\nwe apply sentiment analysis techniques to obtain insights on the type of\nsentiment being expressed in commit messages of the selected commits. We\nobserve that around 45% of the identified commit messages express trust\nemotion.\n
Cited by 0Open access
Amirali Sajadi, Kostadin Damevski, Preetha Chatterjee · Figshare · 2023
A dataset of developer Gitter chat messages annotated with corresponding emotions, sentiments, and topics.
Cited by 0Open access
Sajadi, Amirali, Damevski, Kostadin, Chatterjee, Preetha · Figshare · 2023
A dataset of developer Gitter chat messages annotated with corresponding emotions, sentiments, and topics.
Cited by 0Open access
Mia Mohammad Imran, Preetha Chatterjee, Kostadin Damevski · arXiv (Cornell University) · 2023
Understanding and identifying the causes behind developers' emotions (e.g., Frustration caused by `delays in merging pull requests') can be crucial towards finding solutions to problems and fostering collaboration in open-source communities. Effectively identifying such information in the high volume of communications across the different project channels, such as chats, emails, and issue comments, requires automated recognition of emotions and their causes. To enable this automation, large-scale software engineering-specific datasets that can be used to train accurate machine learning models are required. However, such datasets are expensive to create with the variety and informal nature of software projects' communication channels. In this paper, we explore zero-shot LLMs that are pre-trained on massive datasets but without being fine-tuned specifically for the task of detecting emotion causes in software engineering: ChatGPT, GPT-4, and flan-alpaca. Our evaluation indicates that these recently available models can identify emotion categories when given detailed emotions, although they perform worse than the top-rated models. For emotion cause identification, our results indicate that zero-shot LLMs are effective at recognizing the correct emotion cause with a BLEU-2 score of 0.598. To highlight the potential use of these techniques, we conduct a case study of the causes of Frustration in the last year of development of a popular open-source project, revealing several interesting insights.
Cited by 1Open access
Raha Binte Rashid · 2024
In the dynamic realm of programming communities, the choice of communication platforms significantly shapes collaboration patterns and knowledge exchange dynamics.Emotions play a crucial role in shaping individuals' perceptions, attitudes, and behaviours within these communities, influencing productivity, creativity, and overall well-being.However, while sentiment and emotion analysis in short texts or utterances have been extensively researched, there remains a notable gap in classifying emotions or sentiment at the level of chat conversations.In this thesis we aim to address this gap by undertaking a comprehensive exploration of chat conversations within programming communities surrounding Clojure, Python, and Racket languages, utilizing the popular platforms Discord and Slack.Unlike previous studies focusing on short texts or utterances, we centre our investigation on chat conversation emotion detection.To facilitate this endeavour, we have curated and published an annotated dataset of chat conversations manually classified with Shaver's Tree-structured emotions, encompassing primary and secondary emotions.Our dataset, CloPyRack [1], consolidates disentangled chat conversations from the DISCO and SLACK datasets for the Clojure, Python, and Racket communities.Additionally, leveraging the DISCO and SLACK datasets, we employ a two-step approach, manually classifying a portion of the dataset and utilizing the ALBERT model to classify the remaining conversations.Furthermore, we evaluate the performance of existing emotion detection models, including EMTK, ALBERT, RoBERTa, and DeBERTa, alongside their respective large models, to assess their efficacy in chat conversation emotion detection.Our evaluation reveals that the pre-trained large language model ALBERT outperforms EMTK models, exhibiting approximately a 68.57% higher average F1-score.Moreover, our analysis of the classified datasets for Discord and Slack unveils a pattern of iii
Cited by 0Open access
anonymous · Zenodo (CERN European Organization for Nuclear Research) · 2023
Integrating large language models (LLMs) like ChatGPT into the software development process marks a significant evolution in the field. We perform topic modelling and sentiment analysis on developer interactions, aiming to categorise and understand the prevalent topics and emotional undertones in these conversations. The study addresses three key research questions: identifying predominant topics in developer interactions with ChatGPT (RQ1), examining the relationship between emotions expressed and these topics (RQ2), and exploring how conversation complexity relates to topics and emotions (RQ3). This multifaceted analysis offers insights into developer concerns and preferences, vital for improving AI responses and functionality.
Cited by 0Open access
anonymous · Zenodo (CERN European Organization for Nuclear Research) · 2023
Integrating large language models (LLMs) like ChatGPT into the software development process marks a significant evolution in the field. We perform topic modelling and sentiment analysis on developer interactions, aiming to categorise and understand the prevalent topics and emotional undertones in these conversations. The study addresses three key research questions: identifying predominant topics in developer interactions with ChatGPT (RQ1), examining the relationship between emotions expressed and these topics (RQ2), and exploring how conversation complexity relates to topics and emotions (RQ3). This multifaceted analysis offers insights into developer concerns and preferences, vital for improving AI responses and functionality.
Cited by 0Open access
Rohit Mehra, Vibhu Saujanya Sharma, Vikrant Kaulgud et al. · 2020
Positive affects have been shown to be positively correlated with developer productivity. Moreover, the environment in which the developer sits is important as it has a direct bearing on her emotions. However, in typical software development project setups, it is difficult to mold the surroundings of a developer according to her own needs or wishes. Moreover, large project areas may tend to have multiple distractions that may further negatively affect the developer. Multiple studies have shown that Virtual Reality can be an effective medium to induce positive emotions, with the capability to immerse oneself into virtually created environs, allowing for countless opportunities to surround a developer with what she would want. In this paper, we present our approach to allow a developer to choose her own surrounding environment to work in (say a beach, a park or in space!), while allowing for a real-time feed of her workstation/tools to be embedded in the same for a seamless experience. We believe that this approach will enable better mood/engagement and lower distractions/stress, which may lead to higher productivity and a balanced sense of developer well-being.
Cited by 6
Kashumi Madampe, Rashina Hoda, John Grundy · IEEE Software · 2024
Like all people, software developers feel several emotions – positive and negative – when working on projects. But what are the underlying reasons for these emotions? Are their emotions linked to their work satisfaction and productivity? Can we boost developer satisfaction and productivity by remedying the causes of negative emotions? Agile is the most common software development approach currently used. Based on our empirical industry studies, we propose several solutions to overcome the causes of negative emotions in agile contexts.
Cited by 2
Zhijun Gao, Tianshu Wang, Meina Wang et al. · 2023
This pilot UX study aims to establish a user experience (UX) approach for assessing the quality of developer documentation, specifically for the OceanBase database company. A usability test was designed to examine task completion rates, times, errors, and satisfaction. Additionally, biometric equipment, such as eye-tracking, EEG, facial expression recognition, and measures of visual and mental fatigue, were utilized to analyze participants’ experiences. The PANAS scale was employed to collect self-reported emotions. The hybrid evaluation method revealed that the OceanBase database documentation suffers from poor usability, understanding, and findability. The root causes of these problems include weak functionality, subpar interaction design, lack of conciseness and explanation, and inadequate structure and legibility. Participants experienced negative emotions and increased mental fatigue after using the documentation, indicating a substantial cognitive load. These findings will inform future improvements to the documentation and provide a foundational UX model for developer documentation. The UX study process may also be a reference for practitioners or researchers conducting similar research on technical documents.
Cited by 0
Chromatic Voices · Bulletin of Miscellaneous Information (Royal Gardens Kew) · 2020
A friend, a developer, a seeker of the next good thing. A complex human who wears his emotions on his sleeve and isn't afraid to shout it from the roof tops. Meet Jeff, whose voice colors Aray's vision in Pantone 1955C. A hue that's saturated like a juicy soft, off the branch, warmed by the sun raspberry.
Cited by 0
Syed Fatiul Huq, A. Sadiq, Kazi Sakib · 2020
The outcome of software products primarily depends on the developers, including their emotion or sentiment in a software development environment. Developer emotions have been observed to be correlated to several patterns, for instance, task resolution time, developer turnover, etc. by conducting sentiment analysis on software collaborative artifacts like Commits. This study aims to quantify the impact of those patterns by finding a relation between developer sentiment and software bugs. To do so, Fix-Inducing Changes — changes that introduce bugs to the system — are detected, along with changes that precede or fix those bugs. Sentiment of these changes are determined from their Commit messages using Senti4SD. It is statistically observed that Commits that introduce, precede or fix bugs are significantly more negative than regular Commits, with a higher proportion of emotional (non-neutral) messages. It is also found that a distinction between buggy and correct fixes exists based on the message's neutrality.
Cited by 20
Chalen Westaby, Jake Phillips, Sam Ainslie et al. · European Journal of Probation · 2022
Senior Probation Officer’s (SPOs) in England and Wales work at the ‘front and centre’ of the organisation’s hierarchy. They act as both manager and developer of frontline probation practitioners. Previous research has focused on the emotional labour undertaken by probation practitioners yet there is very little research on the emotional labour of SPOs, even though they must be skilful emotion managers of their own emotions and those they supervise. Using data gathered from interviews with 28 SPOs and managers across England and Wales, we analyse how SPOs’ emotions are ‘controlled’ by senior management, and how SPOs ‘control’ the emotions of frontline workers they supervise. SPOs attempts at managing emotions are resisted by their supervisees, and SPOs resist the emotional displays they are expected to present in their work role. We conclude by considering the impact of emotional labour on SPOs and how best to support them in their role.
Cited by 9Open access
Martin Obaidi, Marc Herrmann, Elisa Schmid et al. · ArXiv.org · 2025
Sentiment analysis is an essential technique for investigating the emotional climate within developer teams, contributing to both team productivity and project success. Existing sentiment analysis tools in software engineering primarily rely on English or non-German gold-standard datasets. To address this gap, our work introduces a German dataset of 5,949 unique developer statements, extracted from the German developer forum Android-Hilfe.de. Each statement was annotated with one of six basic emotions, based on the emotion model by Shaver et al., by four German-speaking computer science students. Evaluation of the annotation process showed high interrater agreement and reliability. These results indicate that the dataset is sufficiently valid and robust to support sentiment analysis in the German-speaking software engineering community. Evaluation with existing German sentiment analysis tools confirms the lack of domain-specific solutions for software engineering. We also discuss approaches to optimize annotation and present further use cases for the dataset.
Cited by 0Open access
Atif Ali Wagan, Shuaiyong Li · Journal of Software Evolution and Process · 2025
ABSTRACT Effective collaboration among software developers relies heavily on their ability to communicate efficiently, with emotions playing a pivotal role in this process. Emotions are widely used in human decision‐making, making automated tools for emotion classification within developer communication channels essential. These tools can enhance productivity and collaboration by increasing awareness of fellow developers' emotions. Previous approaches, such as HOMER, RAKEL, and EmoTxt, have been proposed to classify emotions in Stack Overflow and Jira datasets at a finer granularity. However, these tools face performance challenges. To address these limitations, we aim to enhance multilabeled emotion classification performance by leveraging TextCNN, word embeddings, and hyper‐parameter optimization. We validate the performance of this method by comparing it with the best previous methods for emotion classification in software engineering text. This approach achieves an F1‐Micro score of 84.6001% on the Jira dataset and 76.9366% on the Stack Overflow dataset, showing an improvement of 3.5001% and 8.6366%, respectively. This advancement underscores the potential of this method in improving emotion classification performance, thereby fostering better collaboration and productivity among software developers.
Cited by 1Open access
David Van Nuys, PhD · Bulletin of Miscellaneous Information (Royal Gardens Kew) · 2021
My guest today is Elizabeth Cohn Stuntz Licensed Clinical Social Worker and psychoanalytic psychotherapist. Along with Dr. Marsha Linehan the developer of Dialectical Behavior Therapy, she is co-author of the new book, Coping with Cancer: DBT Skills to Manage Your Emotions and Balance Uncertainty with Hope. This groundbreaking book provides much-needed help for anyone who is facing cancer as well as for the many mental and emotional challenges we all face in these unprecedented times.
Cited by 0
Alexandru Popescu, Joost Broekens, Maarten van Someren · IEEE Transactions on Affective Computing · 2013
In this paper we present GAMYGDALA, an emotional appraisal engine that enables game developers to easily add emotions to their Non-Player Characters (NPC). Our approach proposes a solution that is positioned between event coding of affect, where individual events have predetermined annotated emotional consequences for NPCs, and a full blown cognitive appraisal model. Instead, for an NPC that needs emotions the game developer defines goals and annotates game events with a relation to these goals. Based on this input, GAMYGDALA produces an emotion for that NPC according to the well-known OCC model. In this paper we provide evidence for the following: GAMYGDALA provides black-box Game-AI independent emotion support, is efficient for large numbers of NPCs, and is psychologically grounded.
Cited by 71