Emoticon Recommendation in Microblog Using Affective Trajectory Model

Abstract

Recently with the rise of microblogging service people like to express their feelings through posting microblog articles Together with the articles emoticons are often used to express their affective states However current practice is inconvenient while choosing or tagging emoticons This thesis proposed an emoticon recommendation system based on the content of the post In this study microblog posts are assumed to embed with fluctuating emotions Fixed-sized sliding windows are applied to split the post into several segments for pattern feature mining The feature vectors are further projected to an emoticon space based on an LDA-based model to form emoticon profile sequence as an affective trajectory The k-medoids clustering algorithm with Hausdorff distance was applied to cluster the affective trajectories The recommended emoticon for an input microblog was finally determined by a log-linear model The proposed approach was verified using microblogs crawled from Plurk The results show that our method outperforms the classical LDA approach

Date of Award	2014 Aug 18
Original language	English
Supervisor	Chung-Hsien Wu (Supervisor)