Knowledge discovery of game design features by mining user-generated feedback. (July 2016)

• Record Type: Journal Article
• Authors: Gopinath Bharathi, Ajay Karthic B.; Singh, Abhinav; Tucker, Conrad S.; Nembhard, Harriet B.
• Is Part Of: Computers in human behavior. Volume 60(2016)
• Page Start: 361
• Page End: 371
• Publication Date: 2016-07
• Subjects: Gamification -- Game design features -- Machine learning -- Behavior change -- User engagement; Interactive computer systems -- Periodicals; Man-machine systems -- Periodicals; 004.019
• DOI: 10.1016/j.chb.2016.02.076
• Languages: English
• ISSNs: 0747-5632

Abstract

Abstract: The term "Gamification" is an emerging paradigm that aims to employ game mechanics and game thinking to change behavior. Gamification offers several effective ways to motivate users into action such as challenges, levels and rewards. However, an open research problem is discovering the set of gamification features that consistently result in a higher probability of success for a given task, game or application. The objective of this paper is to bridge this knowledge gap by quantifying the gamification features that are consistently found in successful applications. Knowledge gained from this work will inform designers about the gamification features that lead to higher chances of an application's success, and the gamification features that do not significantly impact the success of an application. The case study presented in this work leverages demographic heterogeneity and scale of applications existing within mobile platforms to evaluate the impact of gamification features on the success or failure of those applications. The successful game design features identified have the potential to be embedded into interactive gamification platforms across various fields such as healthcare, education, military and marketing, in order to maintain or enhance user engagement. Highlights: Automated discovery of game design features that impact success. Game design features combinations discovered through machine learning algorithms. Incorporation of game design features to motivate individuals.