Facilitating apps recommendation in Google Play

Abstract

Purpose The purpose of this paper is to present a system that analyzes trustworthiness and ranks applications to improve the search experience. Design/methodology/approach The system adopts pointwise mutual information to calculate comment semantics. It examines subjective (signed opinions, anonymous opinions and star ratings) and objective factors (download numbers, reputation ratings) before filtering, ranking and displaying). The authors invited three experts to check three categories and compared the results using Spearman and two statistics. Findings A high correlation between the proposed system and the expert ranking system suggests that the system can act as decision support. Research limitations/implications First, the authors have only tested the correlation between the proposed system and an expert ranking system; user satisfaction was not evaluated. The authors plan to conduct a later survey to gather user feedback. Second, the ranking system evaluates applications using fixed weights and disregards time. Therefore, in the future, the authors plan to enable their system to weight recent records over older ones. Practical implications User discussion forums, although helpful, have drawbacks. Not all reviews are trustworthy, and forums provide no filtering mechanisms to combat information overload. The solution to this is the authors’ system that crawls a forum, filters information, analyzes the trustworthiness of each comment and ranks the application for the user. Originality/value This paper develops a formula to analyze the trustworthiness of opinions, enabling the system to act as decision support when no professional advice is available.