Home > Published Issues > 2020 > Volume 11, No. 2, May 2020 >

Opinion Discovery Framework: Toward a Quality Opinion-Centric Platform

Najla Althuniya, Xiaoqing Liu, Joseph W. Sirrianni, and Douglas Adams
University of Arkansas, Fayetteville, AR, USA

Abstract—People use argumentation and deliberation platforms to express and share opinions. As a result, these platforms contain massive opinions where users cannot keep track of or identify where constructive opinions are. In our study, we found that users only view, on average, 3% of the available content. Usually, opinions are discovered by engagement information, impact score or reverse-chronological order but opinions contain substantial information beyond its text. Features for opinions discovery improves the discourse quality and provides an attractive online discussion platform. However, there are no clear feature sets for the opinions that have been identified for searching and discovering opinions in academia or public-debate platforms. This paper proposes a novel innovative framework for opinion selection and discovery. It discovers constructive opinions based on four unique features: engagement, recentness, controversy, and author influence. Therefore, it provides a dynamic discourse incorporating opinion’s features based on users’ preferences. We first defined those features in the cyber-argumentation space. Then, we discuss our new framework that combines those features for opinion search and discovery. An application example on a deliberation dataset has shown that our framework works effectively on discovering and searching constructive opinions.
Index Terms—argumentation, engagement, recentness, search algorithm, search, opinion, controversy, author influence, discovery

Cite: Najla Althuniya, Xiaoqing Liu, Joseph W. Sirrianni, and Douglas Adams, "Opinion Discovery Framework: Toward a Quality Opinion-Centric Platform," Journal of Advances in Information Technology, Vol. 11, No. 2, pp. 48-57, May 2020. doi: 10.12720/jait.11.2.48-57

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.