Proceedings of the 13th International Conference on Mining Software Repositories 2016
DOI: 10.1145/2901739.2901752
|View full text |Cite
|
Sign up to set email alerts
|

Mining valence, arousal, and dominance

Abstract: Similar to other industries, the software engineering domain is plagued by psychological diseases such as burnout, which lead developers to lose interest, exhibit lower activity and/or feel powerless. Prevention is essential for such diseases, which in turn requires early identification of symptoms. The emotional dimensions of Valence, Arousal and Dominance (VAD) are able to derive a person's interest (attraction), level of activation and perceived level of control for a particular situation from textual commu… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

1
27
1
2

Year Published

2019
2019
2023
2023

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 78 publications
(31 citation statements)
references
References 47 publications
1
27
1
2
Order By: Relevance
“…Certain properties of language may be particularly important indicators of community health—specifically, sentiment (or emotion) 2 and gratitude, given the importance of these to individual and interpersonal processes to social health generally and within software programming communities (Algoe, 2012 ; Dabbish, Stuart, Tsay, & Herbsleb, 2012 ; Emmons & Shelton, 2002 ; França, Sharp, & Da Silva, 2014 ; Steinmacher, Conte, Gerosa, & Redmiles, 2015 ; Yoshimura & Berzins, 2017 ). However, consistent with a dynamical systems approach to language (Gibbs & Van Orden, 2012 ; Hodges & Fowler, 2010 ; Paxton, Dale, & Richardson, 2016 ), these patterns should be sensitive to the specific context in which communication occurs (Mäntylä, Adams, Destefanis, Graziotin, & Ortu, 2016 ; Rączaszek‐Leonardi & Kelso, 2008 ) and the person's own relationship with the community (and, by extension, their enculturation into the community; Thorne, Black, & Sykes, 2009 ; Rączaszek‐Leonardi, 2010 ). Therefore, patterns should vary by the community (Port, 2010 ; Thorne et al., 2009 ) and over time (i.e., as members join and leave; Demjén, 2018 ; Rączaszek‐Leonardi & Kelso, 2008 ).…”
Section: Introductionmentioning
confidence: 87%
“…Certain properties of language may be particularly important indicators of community health—specifically, sentiment (or emotion) 2 and gratitude, given the importance of these to individual and interpersonal processes to social health generally and within software programming communities (Algoe, 2012 ; Dabbish, Stuart, Tsay, & Herbsleb, 2012 ; Emmons & Shelton, 2002 ; França, Sharp, & Da Silva, 2014 ; Steinmacher, Conte, Gerosa, & Redmiles, 2015 ; Yoshimura & Berzins, 2017 ). However, consistent with a dynamical systems approach to language (Gibbs & Van Orden, 2012 ; Hodges & Fowler, 2010 ; Paxton, Dale, & Richardson, 2016 ), these patterns should be sensitive to the specific context in which communication occurs (Mäntylä, Adams, Destefanis, Graziotin, & Ortu, 2016 ; Rączaszek‐Leonardi & Kelso, 2008 ) and the person's own relationship with the community (and, by extension, their enculturation into the community; Thorne, Black, & Sykes, 2009 ; Rączaszek‐Leonardi, 2010 ). Therefore, patterns should vary by the community (Port, 2010 ; Thorne et al., 2009 ) and over time (i.e., as members join and leave; Demjén, 2018 ; Rączaszek‐Leonardi & Kelso, 2008 ).…”
Section: Introductionmentioning
confidence: 87%
“…For example, in some cases the mining of opinions might be the target rather than the recognition of actual emotions, such as joy or sadness. (Lin et al 2019) reported poor performance of classifiers designed to detect developers' emotions (e.g., love, joy, fear) when applied to the different task of detecting developers' opinions about software libraries.…”
Section: Sentiment Analysis Tools Should Be Retrained If Possible Rather Than Used Off the Shelfmentioning
confidence: 99%
“…To overcome such limitations, researchers have started developing SE-specific sentiment analysis tools to mine developers' emotions (e.g., Calefato et al (2018a), Ahmed et al (2017), Islam and Zibran (2017), and Chen et al (2019)) and opinions (e.g., (Lin et al 2019;Uddin and Khomh 2017)). In previous benchmarking studies, (Novielli et al 2018b; showed how SE-specific customization gives a boost in accuracy in terms of both agreement with manual annotation and agreement among tools, provided that model-based annotation of emotions is implemented and that a robust gold-standard dataset for retraining is available.…”
Section: Introductionmentioning
confidence: 99%
“…Many researchers in psychology have argued, however, that it is necessary to go beyond categorical emotions [5]. Apart from enabling degrees of emotions in a continuous space, using emotional dimensions offers other advantages such as investigation of cognitive mental states and measurement of productivity and burnout [6].…”
Section: Introductionmentioning
confidence: 99%