Enhancing Twitter Tweet Topic Understanding through Ensemble Learning
Suraj Shinde Patil1, Muskan Jain2, Harsh Ahuja3, Akshay Mathur4
1Suraj Shinde Patil, Department of Computer Science, Sanjay Ghodawat University, Kolhapur (Maharashtra), India.
2Muskan Jain, Department of Computer Science, Dr. A.P.J. Abdul Kalam Technological University, Lucknow (U.P), India.
3Harsh Ahuja, Department of Computer Science, Dr. A.P.J. Abdul Kalam Technological University, Lucknow (U.P), India.
4Akshay Mathur, Department of Computer Science, Manipal University Jaipur, Jaipur (Rajasthan), India.
Manuscript received on 06 November 2023 | Revised Manuscript received on 16 November 2023 | Manuscript Accepted on 15 December 2023 | Manuscript published on 30 December 2023 | PP: 6-12 | Volume-13 Issue-1, December 2023 | Retrieval Number: 100.1/ijitee.A97611213123 | DOI: 10.35940/ijitee.A9761.1213123
Open Access | Editorial and Publishing Policies | Cite | Zenodo | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Since Twitter’s introduction to social media of the hashtag as a content grouping label in 2007, the symbol and its associated usage as a classification la- bel have seen widespread adoption throughout social media and other platforms. While the content of a post can be conveniently classified using said post’s hash- tags, classifying posts that do not contain hashtags proves to be a much more challenging problem. In this paper, we propose a system for identifying a post’s hashtags using only the non-hashtag terms of the post and, by extension, address the issue of classifying the contents of posts that do not contain hashtags.
Keywords: Social Media, Classification, Hashtags, Twitter Data
Scope of the Article: Classification