Abstract:
Recommendation systems usually try to “guess” a user's preferences from the system's view. We study another side of recommendation: active opinion-formation from the pers...Show MoreMetadata
Abstract:
Recommendation systems usually try to “guess” a user's preferences from the system's view. We study another side of recommendation: active opinion-formation from the perspective of the user. In real life, a user's opinion evolves with time and refines when new evidence occurs. Then, how does an online user form his/her own opinion actively in large social networks? The problem has three challenges: the factor, the effect and the open environment. To address those challenges, we investigate: (1) what factors or channels a user will consider, (2) how those channels will take effect, and (3) an incremental approach to incorporate multiple channels. We explore three types of channels: the internal opinion of an individual user, influences from trusted friends, and influences from public channels. A novel simulator, OpinionFormer, is proposed to incorporate those channels incrementally. It differentiates the effects of friends and public channels as well as positive and negative opinions. We validate the performance of OpinionFormer by predicting users' opinions using real-world data sets. Experimental results show that our model can improve accuracy over other models that ignore some channels or that neglect the evolving features.
Date of Conference: 01-04 May 2017
Date Added to IEEE Xplore: 05 October 2017
ISBN Information: