skip to main content
10.1145/2464464.2464512acmconferencesArticle/Chapter ViewAbstractPublication PageswebsciConference Proceedingsconference-collections
research-article

Sentiment and topic analysis on social media: a multi-task multi-label classification approach

Published: 02 May 2013 Publication History

Abstract

Both sentiment analysis and topic classification are frequently used in customer care and marketing. They can help people understand the brand perception and customer opinions from social media, such as online posts, tweets, forums, and blogs. As such, in recent years, many solutions have been proposed for both tasks. However, we believe that the following two problems have not been addressed adequately: (1) Conventional solutions usually treat the two tasks in isolation. When the two tasks are closely related (e.g., posts about "customer care" often have a "negative" tone), exploring their correlation may yield a better accuracy; (2) Each post is usually assigned with only one sentiment label and one topic label. Since social media is, compared to traditional document corpus, more noisy, ambiguous, and sparser, single label classification may not be able to capture the post classes accurately. To address these two problems, in this paper, we propose a multi-task multi-label (MTML) classification model that performs classification of both sentiments and topics concurrently. It incorporates results of each task from prior steps to promote and reinforce the other iteratively. For each task, the model is trained with multiple labels so that they can help address class ambiguity. In the empirical validation, we compare the accuracy of MTML model against four competing methods in two different settings. Results show that MTML produces a much higher accuracy of both sentiment and topic classifications.

References

[1]
Agarwal, A., Xie, B., Vovsha, I., Rambow, O., and Passonneau, R. Sentiment analysis twitter data. In Workshop on Languages in Social Media (2011), 30--38.
[2]
Argyriou, A., odoros Evgeniou, and Pontil, M. Multi-task feature learning. In Conf. on Neural Information Processing Systems (NIPS) (2006), 41--48.
[3]
Ben-David, S., and Schuller, R. Exploiting task relatedness for mulitple task learning. In Annual Conf. on Computational Learning Theory (2003), 567--580.
[4]
Boutell, M. R., Luo, J., Shen, X., and Brown, C. M. Learning multi-label scene classification. Pattern Recognition (2004), 1757--1771.
[5]
Caruana, R. Multitask learning. Mach. Learn. 28 (1997), 41--75.
[6]
Chapelle, O., Shivaswamy, P., Vadrevu, S., Weinberger, K., Zhang, Y., and Tseng, B. Multi-task learning for boosting with application to web search ranking. In ACM KDD (2010), 1189--1198.
[7]
Chua, F. C. T., Cohen, W. W., Betteridge, J., and Lim, E.-P. Community-based classification noun phrases in twitter. In ACM CIKM (2012).
[8]
Clare, A., and King, R. D. Knowledge discovery in multi-label phenotype data. In 5th European Conf. on Principles Data Mining and Knowledge Discovery (2001), 42--53.
[9]
Evgeniou, O., Micchelli, C. A., and Pontil, M. Learning multiple tasks with kernel methods. J. Machine Learning Research 6 (2005), 615--637.
[10]
Evgeniou, O., and Pontil, M. Regularized multi--task learning. In ACM KDD (2004), 109--117.
[11]
Jebara, T. Multi-task feature and kernel selection for svms. In Int'l Conf. on Machine learning (ICML) (2004).
[12]
Jiang, L., Yu, M., Zhou, M., Liu, X., and Zhao, T. Target-dependent twitter sentiment classification. In ACL (2011), 151--160.
[13]
Jin, R., and Ghahramani, Z. Learning with multiple labels. In Conf. on Neural Information Processing Systems (NIPS) (2003).
[14]
Lauser, B., and Hotho, A. Automatic multi-label subject indexing in a multilingual environment. In 7th European Conf. in Research and Advanced Technology for Digital Libraries (2003), 140--151.
[15]
Lee, K., Palsetia, D., Narayanan, R., Patwary, M. M. A., Agrawal, A., and Choudhary, A. Twitter trending topic classification. In IEEE IDCM Workshops (2011), 251--258.
[16]
McCallum, A. K. Multi-label text classification with a mixture model trained by em. In AAAI Workshop on Text Learning (1999).
[17]
McCallum, A. K. Mallet: A machine learning for language toolkit. http://mallet.cs.umass.edu, 2002.
[18]
Nishida, K., Banno, R., Fujimura, K., and Hoshide, T. Tweet classification by data compression. In Int'l Workshop on DETecting and Exploiting Cultural diversiTy on social web (2011), 29--34.
[19]
Nishida, K., Hoshide, T., and Fujimura, K. Improving tweet stream classification by detecting changes in word probability. In ACM SIGIR (2012).
[20]
Tai, F., and Lin, H.-T. Multilabel classification with principal label space transformation. Neural Comput. 24 (2012), 2508--2542.
[21]
Tan, C., Lee, L., Tang, J., Jiang, L., Zhou, M., and Li, P. User-level sentiment analysis incorporating social networks. In ACM KDD (2011), 1397--1405.
[22]
Thabtah, F. A., Cowling, P., and Peng, Y. Mmac: A new multi-class, multi-label associative classification approach. In IEEE ICDM (2004), 217--224.
[23]
Tsoumakas, G., and Katakis, I. Multi-label classification: An overview. Int J. Data Warehousing and Mining 3 (2007), 1--13.
[24]
Wang, X., Wei, F., Liu, X., Zhou, M., and Zhang, M. Topic sentiment analysis in twitter: a graph-based hashtag sentiment classification approach. In ACM CIKM (2011), 1031--1040.
[25]
Xue, Y., Liao, X., Carin, L., and Krishnapuram, B. Multi-task learning for classification with dirichlet process priors. J. Machine Learning Research 8 (2007), 35--63.

Cited By

View all
  • (2024)Supervised multilabel classification techniques for categorising customer requirements during the conceptual phase in the new product developmentEngineering Management in Production and Services10.2478/emj-2024-000316:1(31-47)Online publication date: 11-Apr-2024
  • (2024)CommentVis: Unveiling Comment Insights Through Interactive Visualization Tool2024 IEEE 17th Pacific Visualization Conference (PacificVis)10.1109/PacificVis60374.2024.00050(353-358)Online publication date: 23-Apr-2024
  • (2024)Multi-Task Learning Aspect Based Sentiment Analysis with BERT2024 16th International Conference on Information Technology and Electrical Engineering (ICITEE)10.1109/ICITEE62483.2024.10808387(264-269)Online publication date: 23-Oct-2024
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
WebSci '13: Proceedings of the 5th Annual ACM Web Science Conference
May 2013
481 pages
ISBN:9781450318891
DOI:10.1145/2464464
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 02 May 2013

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. classification
  2. multi-label
  3. multi-task
  4. sentiment analysis
  5. topic analysis

Qualifiers

  • Research-article

Conference

WebSci '13
Sponsor:
WebSci '13: Web Science 2013
May 2 - 4, 2013
Paris, France

Acceptance Rates

Overall Acceptance Rate 245 of 933 submissions, 26%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)43
  • Downloads (Last 6 weeks)1
Reflects downloads up to 20 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2024)Supervised multilabel classification techniques for categorising customer requirements during the conceptual phase in the new product developmentEngineering Management in Production and Services10.2478/emj-2024-000316:1(31-47)Online publication date: 11-Apr-2024
  • (2024)CommentVis: Unveiling Comment Insights Through Interactive Visualization Tool2024 IEEE 17th Pacific Visualization Conference (PacificVis)10.1109/PacificVis60374.2024.00050(353-358)Online publication date: 23-Apr-2024
  • (2024)Multi-Task Learning Aspect Based Sentiment Analysis with BERT2024 16th International Conference on Information Technology and Electrical Engineering (ICITEE)10.1109/ICITEE62483.2024.10808387(264-269)Online publication date: 23-Oct-2024
  • (2024)A novel framework for multi-label feature selection: integrating mutual information and Pythagorean fuzzy CRADISGranular Computing10.1007/s41066-024-00489-z9:3Online publication date: 26-Jun-2024
  • (2023)Using a Classifier Ensemble for Preventing Burnout in University Students: A Study Case in ValparaísoIEEE Access10.1109/ACCESS.2023.332578511(116235-116254)Online publication date: 2023
  • (2022)Where conspiracy theories flourish: A study of YouTube comments and Bill Gates conspiracy theoriesHarvard Kennedy School Misinformation Review10.37016/mr-2020-107Online publication date: 5-Oct-2022
  • (2022)Multi-label emotion classification based on adversarial multi-task learningInformation Processing and Management: an International Journal10.1016/j.ipm.2022.10309759:6Online publication date: 1-Nov-2022
  • (2021)Multilabel Sentiment Prediction by Addressing Imbalanced Class Problem Using OversamplingAdvances in Smart Communication Technology and Information Processing10.1007/978-981-15-9433-5_23(239-249)Online publication date: 16-Feb-2021
  • (2021)An Indonesian Sentiment Classification Model Based on Multi-task LearningAdvances in Natural Computation, Fuzzy Systems and Knowledge Discovery10.1007/978-3-030-70665-4_128(1182-1191)Online publication date: 27-Jun-2021
  • (2021)Discovering underlying sensations of human emotions based on social mediaJournal of the Association for Information Science and Technology10.1002/asi.2441472:4(417-432)Online publication date: 8-Mar-2021
  • Show More Cited By

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media