Title :
A Joint Model for Topic-Sentiment Evolution over Time
Author :
Dermouche, Mohamed ; Velcin, Julien ; Khouas, Leila ; Loudcher, Sabine
Author_Institution :
Univ. de Lyon, Lyon, France
Abstract :
Most existing topic models focus either on extracting static topic-sentiment conjunctions or topic-wise evolution over time leaving out topic-sentiment dynamics and missing the opportunity to provide a more in-depth analysis of textual data. In this paper, we propose an LDA-based topic model for analyzing topic-sentiment evolution over time by modeling time jointly with topics and sentiments. We derive inference algorithm based on Gibbs Sampling process. Finally, we present results on reviews and news datasets showing interpretable trends and strong correlation with ground truth in particular for topic-sentiment evolution over time.
Keywords :
Markov processes; Monte Carlo methods; inference mechanisms; information resources; text analysis; Gibbs sampling process; LDA-based topic model; inference algorithm; joint model; news datasets; static topic-sentiment conjunction extraction; textual data in-depth analysis; topic-sentiment dynamics; topic-sentiment evolution analysis; topic-wise evolution; Accuracy; Analytical models; Correlation; Data mining; Data models; Joints; Mathematical model; joint topic sentiment models; opinion mining; sentiment analysis; time series; topic models; trend analysis;
Conference_Titel :
Data Mining (ICDM), 2014 IEEE International Conference on
Conference_Location :
Shenzhen
Print_ISBN :
978-1-4799-4303-6
DOI :
10.1109/ICDM.2014.82
