Advertisement

A Socio-Temporal Hashtag Recommendation System for Twitter

  • Kuntal Dey
  • Saroj Kaushik
  • Kritika Garg
  • Ritvik Shrivastava
Conference paper
Part of the Studies in Computational Intelligence book series (SCI, volume 813)

Abstract

The hashtag recommendation systems on Twitter have largely focused on analyzing the text content of tweets. In this work, we modify the state-of-the-art existing natural language processing (NLP) technique and deeply ingrain socio-temporal techniques into the overall process, to model a novel hashtag recommendation system. The social aspect of the system aims to make use of the hashtags generated by familiar individuals possess, as well as, the hashtags used by the individual at the past (profile). The temporal aspect aims to age the tweets, thereby ensuring that the more recent hashtags receive higher weights in the process of recommendation. The NLP technique is modified to offer an initial score based upon text embedding of hashtags, and a socio-temporal function and a burst function are applied to generate a final relevance score for hashtags towards a given tweet. The hashtags with top-K relevance scores are recommended to the user.

References

  1. 1.
    Dey, K., Kaushik, S., Lamba, H., Nagar, S.: Man-o-meter: modeling and assessing the evolution of language usage of individuals on microblogs. In: APWeb, pp. 342–355. Springer (2016)Google Scholar
  2. 2.
    Dey, K., Shrivastava, R., Kaushik, S., Subramaniam, L.V.: Emtagger: a word embedding based novel method for hashtag recommendation on twitter. In: ACUMEN Workshop, ICDM (2017)Google Scholar
  3. 3.
    Ding, Z., Qiu, X., Zhang, Q., Huang, X.: Learning topical translation model formicroblog hashtag suggestion. In: IJCAI, pp. 2078–2084 (2013)Google Scholar
  4. 4.
    Ding, Z., Zhang, Z., Huang, X.: Automatic hashtag recommendation for microblogsusing topic-specific translation model. In: Coling, p. 265 (2012)Google Scholar
  5. 5.
    Gong, Y., Zhang, Q.: Hashtag recommendation using attention-based convolutional neural network. In: IJCAI, pp. 2782–2788 (2016)Google Scholar
  6. 6.
    Gong, Y., Zhang, Q., Huang, X.: Hashtag recommendation using dirichlet process mixture models incorporating types of hashtags. In: EMNLP, pp. 401–410 (2015)Google Scholar
  7. 7.
    Kwak, H., Lee, C., Park, H., Moon, S.: What is twitter, a social network or anews media? In: WWW, pp. 591–600. ACM (2010)Google Scholar
  8. 8.
    Liu, Z., Chen, X., Sun, M.: A simple word trigger method for social tagsuggestion. In: EMNLP, pp. 1577–1588 (2011)Google Scholar
  9. 9.
    Mathioudakis, M., Koudas, N.: Twittermonitor: trend detection over the twitter stream. In: SIGMOD, pp. 1155–1158. ACM (2010)Google Scholar
  10. 10.
    Myers, S.A., Zhu, C., Leskovec, J.: Information diffusion and external influence in networks. In: SIGKDD, pp. 33–41. ACM (2012)Google Scholar
  11. 11.
    Sedhai, S., Sun, A.: Hashtag recommendation for hyperlinked tweets. ACM SIGIR, 831–834 (2014)Google Scholar
  12. 12.
    She, J., Chen, L.: Tomoha: topic model-based hashtag recommendation on twitter. In: WWW, pp. 371–372. ACM (2014)Google Scholar
  13. 13.
    Weston, J., Chopra, S., Adams, K.: # tagspace: semantic embeddings fromhashtags. In: EMNLP, pp. 1822–1827 (2014)Google Scholar
  14. 14.
    Yang, J., Leskovec, J.: Patterns of temporal variation in online media. In: WSDM, pp. 177–186. ACM (2011)Google Scholar
  15. 15.
    Zangerle, E., Gassler, W., Specht, G.: Recommending #-tags in twitter. SASWeb 730, 67–78 (2011)Google Scholar
  16. 16.
    Zhang, Q., Gong, Y., Sun, X., Huang, X.: Time-aware personalized hashtag recommendation on social media. In: COLING, pp. 203–212 (2014)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Kuntal Dey
    • 1
  • Saroj Kaushik
    • 2
  • Kritika Garg
    • 3
  • Ritvik Shrivastava
    • 4
  1. 1.IBM ResearchNew DelhiIndia
  2. 2.Indian Institute of TechnologyDelhiIndia
  3. 3.Ch. Brahm Prakash GECDelhiIndia
  4. 4.Columbia UniversityNew YorkUSA

Personalised recommendations