Date of Award
Doctor of Science in Information Systems
The online petition has become one of the most important channels of civic participation. Most of the state-of-the-art online platforms, however, tend to use simple indicators (such as popularity) to rank petitions, hence creating a situation where the most popular petitions dominate the rank and attract most people’s attention. For the petitions which focus on specific issues, they are often in a disadvantageous position on the list. For example, a petition for local environment problem may not be seen by many people who are really concerned with it, simply because it takes multiple pages to reach it. Therefore, the simple ranking mechanism adopted by most of the online petition platforms cannot effectively link most petitions with those who are really concerned with them. According to previous studies online, petitions seriousness has been questioned due to the rare chance of succeeding. At most, less than 10% of online petitions get the chance to fulfill their causes.
To solve this problem, we present a design of a novel recommender system (PETREC). It leverages social interaction features, psycholinguistic features, and latent topic features to provide a personalized ranking to different users. Hence, it can give users better petition recommendations fitting their unique concerns. We evaluate PETREC against matrix factorization collaborative filtering and content-based filtering with the bag of words (Bow) features as two baseline recommenders for benchmarking. PETREC prediction performance outperformed Matrix factorization collaborative filtering, Bow petition-based content filtering, and Bow user-based content filtering with 4.2%, 1.7%, and 2.8% respectively as improvements in Root Mean Square Error (RMSE).
The recommendation system described in this paper has potential to improve the user experience of online petition platforms. Thus, it is possible that it could encourage more public participation. Eventually, it will help the citizens to make a real difference through actively participating in online petitions that are matching their personalized concerns.
Elnoshokaty, Ahmed, "Hybrid Recommender for Online Petitions with Social Network and Psycholinguistic Features" (2018). Masters Theses & Doctoral Dissertations. 342.