Supervised intensive topic models for emotion detection over short text

Yanghui RAO*, Jianhui PANG, Haoran XIE, An LIU, Tak-Lam WONG, Qing LI, Fu Lee WANG

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Research

7 Citations (Scopus)


With the emergence of social media services, documents that only include a few words are becoming increasingly prevalent. More and more users post short messages to express their feelings and emotions through Twitter, Flickr, YouTube and other apps. However, the sparsity of word co-occurrence patterns in short text brings new challenges to emotion detection tasks. In this paper, we propose two supervised intensive topic models to associate latent topics with emotional labels. The first model constrains topics to relevant emotions, and then generates document-topic probability distributions. The second model establishes association among biterms and emotions by topics, and then estimates word-emotion probabilities. Experiments on short text emotion detection validate the effectiveness of the proposed models.
Original languageEnglish
Title of host publicationDatabase Systems for Advanced Applications : 22nd International Conference, DASFAA 2017, Suzhou, China, March 27-30, 2017, proceedings, part I
EditorsSelçuk CANDAN, Lei CHEN, Torben Bach PEDERSEN, Lijun CHANG, Wen HUA
PublisherSpringer International Publishing AG
Number of pages15
ISBN (Electronic)9783319557533
ISBN (Print)9783319557526
Publication statusPublished - 2017
Externally publishedYes
Event22nd International Conference on Database Systems for Advanced Applications - Suzhou, China
Duration: 27 Mar 201730 Mar 2017

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference22nd International Conference on Database Systems for Advanced Applications
Abbreviated titleDASFAA 2017

Bibliographical note

We are grateful to the anonymous reviewers for their valuable comments on this manuscript. The research has been supported by the National Natural Science Foundation of China (61502545, 61572336), two grants from the Research Grants Council of the Hong Kong Special Administrative Region, China (UGC/FDS11/E03/16 and UGC/FDS11/E06/14), the Start-Up Research Grant (RG 37/2016-2017R), and the Internal Research Grant (RG 66/2016-2017) of The Education University of Hong Kong.


  • Topic model
  • Emotion detection
  • Short text analysis


Dive into the research topics of 'Supervised intensive topic models for emotion detection over short text'. Together they form a unique fingerprint.

Cite this