USING HASHTAG GRAPH-BASED TOPIC MODEL TO CONNECT SEMANTICALLY-RELATED WORDS WITHOUT CO-OCCURRENCE IN MICROBLOGS
0 likes227 views
This paper presents a hashtag graph-based topic model (HGTN) for analyzing microblogs, particularly Twitter, to overcome challenges such as sparsity and informality in tweets. By leveraging user-generated hashtags as semi-structured data, HGTN enhances semantic relations between words and improves topic modeling performance over conventional methods. The effectiveness of HGTN is demonstrated through experiments on real-world tweet datasets, indicating its ability to produce coherent topics and address noise issues in tweet clustering and classification.
![CONTACT: PRAVEEN KUMAR. L (, +91 – 9791938249)
MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com
Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com
significant improvement on the performance of content mining tasks, such as
tweet clustering, hashtag clustering and hashtag classification. HGTM discovers
more readable and distinguishable topics than the stat-of-the-art models as
well. This paper shows one effective alternative of utilizing usercontributed
hashtags for tweet topic modeling to handle both sparseness and noise in
tweets. However, there are still many questions which need to be explored.
For example, we would like to explore reasonable and effective ways of
combining multimodal hash tag relations for tweet modelling and to model
time
REFERENCES
[1] D. M. Blei, A. Y. Ng, and M. I. Jordan, “Latent Dirichlet Allocation,” the
Journal of machine Learning research, vol. 3, pp. 993–1022, 2003
[2] S. C. Deerwester, S. T. Dumais, T. K. Landauer, G. W. Furnas, and R. A.
Harshman, “Indexing by latent semantic analysis,” JASIS, vol. 41, no. 6, pp.
391–407, 1990.
[3] S. Vieweg, A. L. Hughes, K. Starbird, and L. Palen, “Microblogging during two
natural hazards events: What Twitter may contribute to situational
awareness,” in Proceedings of the SIGCHI Conference on Human Factors in
Computing Systems, ser. CHI ’10. New York, NY, USA: ACM, 2010, pp. 1079–
1088.](https://image.slidesharecdn.com/usinghashtaggraph-basedtopicmodels-160722073236/85/USING-HASHTAG-GRAPH-BASED-TOPIC-MODEL-TO-CONNECT-SEMANTICALLY-RELATED-WORDS-WITHOUT-CO-OCCURRENCE-IN-MICROBLOGS-3-320.jpg)
![CONTACT: PRAVEEN KUMAR. L (, +91 – 9791938249)
MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com
Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com
[4] Y. Chen, H. Amiri, Z. Li, and T.-S. Chua, “Emerging topic detection for
organizations from microblogs,” in Proceedings of the 36th International ACM
SIGIR Conference on Research and Development in Information Retrieval, ser.
SIGIR ’13. New York, NY, USA: ACM, 2013, pp. 43– 52.
[5] J. Chen, R. Nairn, L. Nelson, M. Bernstein, and E. Chi, “Short and tweet:
Experiments on recommending content from information streams,” in
Proceedings of the SIGCHI Conference on Human Factors in Computing
Systems, ser. CHI ’10. New York, NY, USA: ACM, 2010, pp. 1185– 1194.
[6] K. Tao, F. Abel, Q. Gao, and G.-J. Houben, “TUMS: Twitter-based user
modeling service,” in The Semantic Web: ESWC 2011 Workshops, ser. Lecture
Notes in Computer Science, R. Garca-Castro, D. Fensel, and G. Antoniou, Eds.
Springer Berlin Heidelberg, 2012, vol. 7117, pp. 269–283.
[7] A. Dong, R. Zhang, P. Kolari, J. Bai, F. Diaz, Y. Chang, Z. Zheng, and H. Zha,
“Time is of the essence: Improving recency ranking using Twitter data,” in
Proceedings of the 19th International Conference on World Wide Web, ser.
WWW ’10. New York, NY, USA: ACM, 2010, pp. 331–340.
[8] T. Hofmann, “Probabilistic latent semantic indexing,” in Proceedings of the
22Nd Annual International ACM SIGIR Conference on Research and
Development in Information Retrieval, ser. SIGIR ’99. New York, NY, USA: ACM,
1999, pp. 50–57.](https://image.slidesharecdn.com/usinghashtaggraph-basedtopicmodels-160722073236/85/USING-HASHTAG-GRAPH-BASED-TOPIC-MODEL-TO-CONNECT-SEMANTICALLY-RELATED-WORDS-WITHOUT-CO-OCCURRENCE-IN-MICROBLOGS-4-320.jpg)
![CONTACT: PRAVEEN KUMAR. L (, +91 – 9791938249)
MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com
Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com
[9] L. Hong and B. D. Davison, “Empical study of topic modeling in Twitter,” in
Proceedings of the First Workshop on Social Media Analytics, ser. SOMA ’10.
New York, NY, USA: ACM, 2010, pp. 80–88.
[10] R. Mehrotra, S. Sanner, W. Buntine, and L. Xie, “Improving LDA topic
models for microblogs via tweet pooling and automatic labeling,” in
Proceedings of the 36th International ACM SIGIR Conference on Research and
Development in Information Retrieval, ser. SIGIR ’13. New York, NY, USA: ACM,
2013, pp. 889–892.](https://image.slidesharecdn.com/usinghashtaggraph-basedtopicmodels-160722073236/85/USING-HASHTAG-GRAPH-BASED-TOPIC-MODEL-TO-CONNECT-SEMANTICALLY-RELATED-WORDS-WITHOUT-CO-OCCURRENCE-IN-MICROBLOGS-5-320.jpg)
USING HASHTAG GRAPH-BASED TOPIC MODEL TO CONNECT SEMANTICALLY-RELATED WORDS WITHOUT CO-OCCURRENCE IN MICROBLOGS
- 1. CONTACT: PRAVEEN KUMAR. L (, +91 – 9791938249) MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com USING HASHTAG GRAPH-BASED TOPIC MODEL TO CONNECT SEMANTICALLY- RELATED WORDS WITHOUT CO-OCCURRENCE IN MICROBLOGS ABSTRACT: In this paper, we introduce a new topic model to understand the chaotic microblogging environment by using hashtag graphs. Inferring topics on Twitter becomes a vital but challenging task in many important applications. The shortness and informality of tweets leads to extreme sparse vector representations with a large vocabulary. This makes the conventional topic models (e.g., Latent Dirichlet Allocation and Latent Semantic Analysis ) fail to learn high quality topic structures. Tweets are always showing up with rich user-generated hashtags. The hashtags make tweets semi-structured inside and semantically related to each other. Since hashtags are utilized as keywords in tweets to mark messages or to form conversations, they provide an additional path to connect semantically related words. In this paper, treating tweets as semi-structured texts, we propose a novel topic model, denoted as Hashtag Graph-based Topic Model (HGTM) to discover topics of tweets. By utilizing hashtag relation information in hashtag graphs, HGTM is able to discover word semantic relations even if words are not co-occurred within a specific tweet. With this method, HGTM successfully alleviates the sparsity problem. Our investigation illustrates that the user-contributed hashtags could serve as weakly-supervised information for topic modeling, and the relation
- 2. CONTACT: PRAVEEN KUMAR. L (, +91 – 9791938249) MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com between hashtags could reveal latent semantic relation between words. We evaluate the effectiveness of HGTM on tweet (hashtag) clustering and hashtag classification problems. Experiments on two real-world tweet data sets show that HGTM has strong capability to handle sparseness and noise problem in tweets. Furthermore, HGTM can discover more distinct and coherent topics than the state-of-the-art baselines. CONCLUSION: Uncovering topics within tweets has become a vital task for widespread content analysis and social media mining. Different from modeling normal text, tweet mining has suffered a great deal of sparseness and informality problems. In this work, we consider that users have provided hashtags as a powerful and valuable data source in the vast amount of tweets on the web. This paper presents HGTM that first introduces the hashtag relation graphs as weakly- supervised information for tweet semantic modeling. We demonstrate that hashtag graphs contain reliable information to bridge semantically-related words in sparse short texts. HGTM can enhance semantic relations between tweets and reduce noise at the same time. Compared to single document oriented topic models (e.g., LSA, LDA, ATM, TWTM, TWDA), HGTM has a better ability to capture semantic relations between words with or without co- occurrence by utilizing the wisdom of crowds from user-generated hashtags. The model provides a more robust solution for tweet modeling than aggregation strategies with traditional topic models. We also prove that LDA framework inherently can not benefit from hashtag graphs. We achieve
- 3. CONTACT: PRAVEEN KUMAR. L (, +91 – 9791938249) MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com significant improvement on the performance of content mining tasks, such as tweet clustering, hashtag clustering and hashtag classification. HGTM discovers more readable and distinguishable topics than the stat-of-the-art models as well. This paper shows one effective alternative of utilizing usercontributed hashtags for tweet topic modeling to handle both sparseness and noise in tweets. However, there are still many questions which need to be explored. For example, we would like to explore reasonable and effective ways of combining multimodal hash tag relations for tweet modelling and to model time REFERENCES [1] D. M. Blei, A. Y. Ng, and M. I. Jordan, “Latent Dirichlet Allocation,” the Journal of machine Learning research, vol. 3, pp. 993–1022, 2003 [2] S. C. Deerwester, S. T. Dumais, T. K. Landauer, G. W. Furnas, and R. A. Harshman, “Indexing by latent semantic analysis,” JASIS, vol. 41, no. 6, pp. 391–407, 1990. [3] S. Vieweg, A. L. Hughes, K. Starbird, and L. Palen, “Microblogging during two natural hazards events: What Twitter may contribute to situational awareness,” in Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, ser. CHI ’10. New York, NY, USA: ACM, 2010, pp. 1079– 1088.
- 4. CONTACT: PRAVEEN KUMAR. L (, +91 – 9791938249) MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com [4] Y. Chen, H. Amiri, Z. Li, and T.-S. Chua, “Emerging topic detection for organizations from microblogs,” in Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval, ser. SIGIR ’13. New York, NY, USA: ACM, 2013, pp. 43– 52. [5] J. Chen, R. Nairn, L. Nelson, M. Bernstein, and E. Chi, “Short and tweet: Experiments on recommending content from information streams,” in Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, ser. CHI ’10. New York, NY, USA: ACM, 2010, pp. 1185– 1194. [6] K. Tao, F. Abel, Q. Gao, and G.-J. Houben, “TUMS: Twitter-based user modeling service,” in The Semantic Web: ESWC 2011 Workshops, ser. Lecture Notes in Computer Science, R. Garca-Castro, D. Fensel, and G. Antoniou, Eds. Springer Berlin Heidelberg, 2012, vol. 7117, pp. 269–283. [7] A. Dong, R. Zhang, P. Kolari, J. Bai, F. Diaz, Y. Chang, Z. Zheng, and H. Zha, “Time is of the essence: Improving recency ranking using Twitter data,” in Proceedings of the 19th International Conference on World Wide Web, ser. WWW ’10. New York, NY, USA: ACM, 2010, pp. 331–340. [8] T. Hofmann, “Probabilistic latent semantic indexing,” in Proceedings of the 22Nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, ser. SIGIR ’99. New York, NY, USA: ACM, 1999, pp. 50–57.
- 5. CONTACT: PRAVEEN KUMAR. L (, +91 – 9791938249) MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com [9] L. Hong and B. D. Davison, “Empical study of topic modeling in Twitter,” in Proceedings of the First Workshop on Social Media Analytics, ser. SOMA ’10. New York, NY, USA: ACM, 2010, pp. 80–88. [10] R. Mehrotra, S. Sanner, W. Buntine, and L. Xie, “Improving LDA topic models for microblogs via tweet pooling and automatic labeling,” in Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval, ser. SIGIR ’13. New York, NY, USA: ACM, 2013, pp. 889–892.