ITEE-DP: Affect Detection in the Social Programmer Ecosystem

Tuesday, April 4, 2017 to Thursday, April 6, 2017

Information Technology and Electrical Engineering Doctoral Programme

Lecturer: Assistant Professor Nicole Novielli, University of Bari, Italy

Date: April 4-6, 2017

Time & Room:

Tuesday, April 4: 9:00-12:00 TS128, 12:00-14:00 IT105, 14:00-16:00 TS128
Wedesday, April 5: 9:00-16:00 131 (former TF105)
Thursday, April 6: 9:00-12:00 M101, 12:00-16:00 131 (former TF105)

Linnanmaa Campus Map

Registration here

Course overview

Motivation. Software engineering involves a large amount of social interaction, as programmers often need to cooperate with others, whether directly or indirectly. However, we have become fully aware of the importance of social aspects in software engineering activities only over the last decade. In fact, it was not until the recent diffusion and massive adoption of social media that we could witness the rise of the “social programmer” and the surrounding ecosystem. Social media has deeply influenced the design of software development-oriented tools such as GitHub (i.e., a social coding site) and Stack Overflow (i.e., a community-based question answering site). Stack Overflow, in particular, is an example of an online community where social programmers do networking by reading and answering others’ questions, thus participating in the creation and diffusion of crowdsourced knowledge and software documentation.

One of the biggest drawbacks of computer-mediated communication is to appropriately convey sentiment through text. While display rules for emotions exist and are widely accepted for interaction in traditional face-to-face communication, web users are not necessarily prepared for effectively dealing with the social media barriers to non-verbal communication. Thus, the design of systems and mechanisms for the development of emotional awareness between communicators is an important technical and social challenge for research related to computer-supported collaboration and social computing. As a consequence, a recent research trend has emerged to study the role of affect in the social programmer ecosystem, by applying sentiment analysis to the content available in sites such as GitHub and Stack Overflow, as well as in other asynchronous communication artifacts such as comments in issue tracking systems.

Contents. This course surveys the state-of-the-art in sentiment analysis tools, with particular focus on sentiment analysis on user-generated content in the social web (i.e, microblogging data, users’ reviews) and examines to what extent they are able to detect affective expressions in communication traces left by software developers (i.e., in discussion threads in technical community-based question-answering or issue tracking systems). A discussion is offered about the advantages and limitations of choosing sentiment polarity and strength as an appropriate way to operationalize affective states in empirical studies. Finally, open challenges and opportunities of affective software engineering are discussed, with special focus on the need to combine cognitive emotion modeling with affective computing and natural language processing techniques to build large-scale, robust approaches for sentiment detection in software engineering.

The course will feature both lectures and practical sessions. The latter, in particular, will show how to use state-of-the art resources to sentiment analysis, with particular focus to publicily available tools (such as SentiStrength) and dictionaries (such as SentiWordNet, LIWC, or WordNet Affect). Available dataset for sentiment analysis in the social web will be also presented and discussed.

Short Bio

Nicole Novielli is an Assistant Professor at the Department of Computer Science of the University of Bari, Italy. Her expertise is in Affective Computing. She received a Ph.D. in Computer Science from the University of Bari in May 2010 discussing a thesis on “Lexical Semantics of Dialogue Act”. In 2012 she joined the COLLAB research group, whose research is in Software Engineering and Computer-Supported Cooperative Work, with special focus on collaborative software development.

Since 2006, her research is on affect modeling and detection in natural language interaction. She is broadly interested in how to recognize and exploit affective and cognitive states in human-computer interaction and in computer-supported cooperative work. Currently, she is working on the role of emotions in community-based Question & Answering and on sentiment analysis in microblogging.  She is the Principal Investigator of ‘EmoQuest - Investigating the Role of Emotions in Online Question & Answer Sites’, a three-year research project funded by the Italian Ministry of Education, Universities and Research.

She has served on the PCs for several international conferences and workshops, including the International Conference on Affective Computing and Intelligent Interaction (ACII), the main forum for research on affective computing. Nicole was involved in the organization of international events including the SEmotion workshop at ICSE 2016 and 2017 (co-chair), ICGSE ‘13 (publicity team), and Sentipolc ‘16 (co-organizer), the sentiment polarity evaluation campaign on microblogging in Italian language. Nicole has published more than 60 papers in peer-reviewed international journals, conferences, and workshops. Since 2011, she is active in technology transfer. She is CTO and co-founder of a startup company that develops mobile solutions for promotion of events through gamification. She organized several events for promoting innovation and entrepreneurship in ICT, including hackathons, courses on developing scalable business based on mobile technologies, and an open innovation summer camp on language technologies.

Detailed program

### Day 1 (5 hours)

9-12: Lecture (3 hours) 

  • Introduction: Personal info & course description (~15 min)
  • Part 1 - Theoretical Background (Affect Modeling)
  • Part 2 - Mining Opinions and Emotions from Text

 (15 mins) Break

  • Part 3 – Emerging Tasks and Key Applications

12-13: Lunch break

13-15: Lab (2 hours)

  • Practicum: Sentiment Analysis with Publicly Available Sentiment Analysis tools

 

### Day 2 (5 hours)

9-12: Lecture (3 hours) 

  • Part 4 - An Overview on Lexical Resources for Sentiment Analysis

 (15 mins) Break

  • Part 5 – Classifier Models for Sentiment

12-13: Lunch break

13-15: Lab (2 hours)

  • Practicum: Scoring words with Sentiment Lexicons

### Day 3 (6 hours)

9-12: Lecture (3 hours) 

  • Part 6 -Affect Detection in the Social Programmer Ecosystem: Open Challenges
    • A Review of Affective Computing Studies in Software Engineering
    • Opportunities and Open Challenges

(15 mins) Break

  • Part 5 – SE-specific Datasets and Lexical Resources

12-13: Lunch break

13-16: Lab (3 hours)

  • Practicum: Build your own classifier!

Relevant readings

  1. F. Calefato, F. Lanubile, M. C. Marasciulo, and N. Novielli, “Mining successful answers in stack overflow,” in Proceedings of the 12th Working Conference on Mining Software Repositories, ser. MSR ’15. Piscataway, NJ, USA: IEEE Press, 2015, pp. 430–433. 

  2. V. Carofiglio, F. d. Rosis, and N. Novielli, “Cognitive Emotion Modeling in Natural Language Communication”. London: Springer London, 2009, pp.23–44. 

  3. D. Graziotin, X. Wang, and P. Abrahamsson, “The Affect of software developers: common misconceptions and measurements”, 2015, in Proceedings of the 8th International Workshop on Cooperative and Human Aspects of Software Engineering (CHASE), 2015, IEEE/ACM.
  4. E. Guzman and B. Bruegge, “Towards emotional awareness in software development teams,” in Proceedings of the 2013 9th Joint Meeting on Foundations of Software Engineering, ser. ESEC/FSE 2013. New York, NY, USA: ACM, 2013, pp. 671–674.
  5. R. Jongeling, S. Datta, and A. Serebrenik, “On negative results when using sentiment analysis tools for software engineering research,” in Empirical Software Engineering,2017, doi:10.1007/s10664-016-9493-x
  6. M. Mäntylä, B. Adams, G. Destefanis, D. Graziotin, and M. Ortu, “Mining valence, arousal, and dominance: Possibilities for detecting burnout and productivity?” in Proceedings of the 13th International Conference on Mining Software Repositories, ser. MSR ’16. New York, NY, USA: ACM, 2016, pp. 247–258. 

  7. A. Murgia, P. Tourani, B. Adams, and M. Ortu, “Do developers feel emotions? an exploratory analysis of emotions in software artifacts,” in Proceedings of the 11th Working Conference on Mining Software Repositories, ser. MSR 2014. New York, NY, USA: ACM, 2014, pp. 262–271.
  8. N. Novielli, F. Calefato, and F. Lanubile, “The challenges of sentiment detection in the social programmer ecosystem,” in Proceedings of the 7th International Workshop on Social Software Engineering, ser. SSE 2015. New York, NY, USA: ACM, 2015, pp. 33–40. 

  9. B. Pang and L. Lee, “Opinion mining and sentiment analysis,” Found. Trends Inf. Retr., vol. 2, no. 1-2, pp. 1–135, Jan. 2008.
  10. J. Russell, “A circumplex model of affect,” Journal of personality and social psychology, vol. 39, no. 6, pp. 1161–1178, 1980.
  11. M. Thelwall, K. Buckley, and G. Paltoglou, “Sentiment strength detection for the social web,” J. Am. Soc. Inf. Sci. Technol., vol. 63, no. 1, pp. 163–173, 2012. Available: http://sentistrength.wlv.ac.uk

More information: Mika Mäntylä

Add to calendar

Back to events

Last updated: 6.3.2017