Abstract
Sentiment analysis and emotion mining techniques are increasingly being used in the field of software engineering. However, the experiments conducted so far have not yielded high accuracy results. Researchers indicate a lack of adaptation of the methods of emotion mining to the specific context of the domain as the main cause of this situation. The article describes research aimed at examining whether the adaptation of the lexicon with emotional intensity of words in the context of software engineering improves the reliability of sentiment analysis. For this purpose, a new lexicon is developed in which words are evaluated as if they were used in the field of software engineering. A comparative experiment of emotion mining based on a generic and a software engineering specific lexicon does not reveal any significant differences in the results.
Highlights
Hochschild’s book ‘‘The Managed Heart’’, published in 1983, initiated the research of emotions in the workplace
Its purpose was to determine if using sentiment analysis tools it is possible to detect periods of positive or negative feelings in the community of Apache projects
Based on the study results they concluded that inducing domain-dependent lexicons may overcome the sentiment analysis limitations [20]
Summary
Hochschild’s book ‘‘The Managed Heart’’, published in 1983, initiated the research of emotions in the workplace. The development of computer-aided emotion recognition methods in the 21st century [2] has given new impetus to undertake research on the role of emotions in various fields. According to the Web of Science database, the number of articles on emotion recognition is growing exponentially. Studies on the role of emotions in the workplace are conducted, among others, in the software engineering domain. It is generally accepted that emotions and moods affect the work of software developers, just like many other professionals [3]. Several studies revealed correlation between emotions and productivity [4]–[6]. One of the emerging directions of research is the analysis of the IT artifacts to detect the emotions of the authors. Due to the access to a large number of artifacts associated with IT projects, unlike other
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have