Authors:
Mohammed Anany
;
Heba Hussien
;
Sherif G. Aly
and
Nourhan Sakr
Affiliation:
Department of Computer Science and Engineering, The American University in Cairo, Cairo and Egypt
Keyword(s):
Software Productivity, Developer Productivity, Emotions, Affects, Evaluation, Measurement, Influence.
Related
Ontology
Subjects/Areas/Topics:
Aggregation, Classification and Tracking
;
Data Manipulation
;
Sensor Networks
Abstract:
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 understand
ing 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.
(More)