Abstract
Social media data are produced continuously by a large and uncontrolled number of users. The dynamic nature of such data requires the sentiment and topic analysis model to be also dynamically updated, capturing the most recent language use of sentiments and topics in text. We propose a dynamic Joint Sentiment-Topic model (dJST) which allows the detection and tracking of views of current and recurrent interests and shifts in topic and sentiment. Both topic and sentiment dynamics are captured by assuming that the current sentiment-topic-specific word distributions are generated according to the word distributions at previous epochs. We study three different ways of accounting for such dependency information: (1) Sliding window where the current sentiment-topic word distributions are dependent on the previous sentiment-topic-specific word distributions in the last S epochs; (2) skip model where history sentiment topic word distributions are considered by skipping some epochs in between; and (3) multiscale model where previous long- and shorttimescale distributions are taken into consideration. We derive efficient online inference procedures to sequentially update the model with newly arrived data and show the effectiveness of our proposed model on the Mozilla add-on reviews crawled between 2007 and 2011.
Original language | English |
---|---|
Article number | 6 |
Number of pages | 21 |
Journal | ACM Transactions on Intelligent Systems and Technology |
Volume | 5 |
Issue number | 1 |
DOIs | |
Publication status | Published - Dec 2013 |
Fingerprint
Bibliographical note
© Copyright: 2013 ACM.Funding: EPSRC [EP/J020427/1]; EC [257859]; Royal Academy of Engineering, UK.
Keywords
- dynamic joint sentiment-topic model
- opinion mining
- sentiment analysis
- topic model
Cite this
}
Dynamic joint sentiment-topic model. / He, Yulan; Lin, Chenghua; Gao, Wei; Wong, Kam-Fai.
In: ACM Transactions on Intelligent Systems and Technology, Vol. 5, No. 1, 6, 12.2013.Research output: Contribution to journal › Article
TY - JOUR
T1 - Dynamic joint sentiment-topic model
AU - He, Yulan
AU - Lin, Chenghua
AU - Gao, Wei
AU - Wong, Kam-Fai
N1 - © Copyright: 2013 ACM. Funding: EPSRC [EP/J020427/1]; EC [257859]; Royal Academy of Engineering, UK.
PY - 2013/12
Y1 - 2013/12
N2 - Social media data are produced continuously by a large and uncontrolled number of users. The dynamic nature of such data requires the sentiment and topic analysis model to be also dynamically updated, capturing the most recent language use of sentiments and topics in text. We propose a dynamic Joint Sentiment-Topic model (dJST) which allows the detection and tracking of views of current and recurrent interests and shifts in topic and sentiment. Both topic and sentiment dynamics are captured by assuming that the current sentiment-topic-specific word distributions are generated according to the word distributions at previous epochs. We study three different ways of accounting for such dependency information: (1) Sliding window where the current sentiment-topic word distributions are dependent on the previous sentiment-topic-specific word distributions in the last S epochs; (2) skip model where history sentiment topic word distributions are considered by skipping some epochs in between; and (3) multiscale model where previous long- and shorttimescale distributions are taken into consideration. We derive efficient online inference procedures to sequentially update the model with newly arrived data and show the effectiveness of our proposed model on the Mozilla add-on reviews crawled between 2007 and 2011.
AB - Social media data are produced continuously by a large and uncontrolled number of users. The dynamic nature of such data requires the sentiment and topic analysis model to be also dynamically updated, capturing the most recent language use of sentiments and topics in text. We propose a dynamic Joint Sentiment-Topic model (dJST) which allows the detection and tracking of views of current and recurrent interests and shifts in topic and sentiment. Both topic and sentiment dynamics are captured by assuming that the current sentiment-topic-specific word distributions are generated according to the word distributions at previous epochs. We study three different ways of accounting for such dependency information: (1) Sliding window where the current sentiment-topic word distributions are dependent on the previous sentiment-topic-specific word distributions in the last S epochs; (2) skip model where history sentiment topic word distributions are considered by skipping some epochs in between; and (3) multiscale model where previous long- and shorttimescale distributions are taken into consideration. We derive efficient online inference procedures to sequentially update the model with newly arrived data and show the effectiveness of our proposed model on the Mozilla add-on reviews crawled between 2007 and 2011.
KW - dynamic joint sentiment-topic model
KW - opinion mining
KW - sentiment analysis
KW - topic model
UR - http://www.scopus.com/inward/record.url?scp=84891775892&partnerID=8YFLogxK
U2 - 10.1145/2542182.2542188
DO - 10.1145/2542182.2542188
M3 - Article
AN - SCOPUS:84891775892
VL - 5
JO - ACM Transactions on Intelligent Systems and Technology
JF - ACM Transactions on Intelligent Systems and Technology
SN - 2157-6904
IS - 1
M1 - 6
ER -