Thesis
Design and evaluation of a Twitter hashtag recommendation system
Washington State University
Master of Science (MS), Washington State University
2014
Handle:
https://hdl.handle.net/2376/102781
Abstract
Twitter has evolved into a powerful communication and information sharing tool used by millions of people around the world to post what is happening now. A hashtag, a keyword or a key phrase prefixed with a hash symbol (#), is a key feature in Twitter to organize tweets and facilitate effective search among a massive volume of data. In this paper, we propose an automatic hashtag recommendation system that helps users find hashtags that are emerging in real-time and also related to their interests. We build two inverted index lists for terms and hashtags in the data set to increase the speed and efficiency of full text search. For hashtag ranking, we employ a variation of the TF-IDF weighting scheme that considers hashtag relevancy as well as data sparseness which is one of key challenges in analyzing microblog data. Experiments on a large Twitter data set demonstrated that our method successfully yields relevant hashtags to user's interest and the performance is more stable and reliable than ranking tags based on tweet content similarity
Metrics
56 File views/ downloads
11 Record Views
Details
- Title
- Design and evaluation of a Twitter hashtag recommendation system
- Creators
- Eriko Otsuka
- Contributors
- David Chiu (Degree Supervisor)Scott Andrew Wallace (Degree Supervisor)
- Awarding Institution
- Washington State University
- Academic Unit
- Electrical Engineering and Computer Science, School of
- Theses and Dissertations
- Master of Science (MS), Washington State University
- Publisher
- Washington State University; [Pullman, Washington] :
- Identifiers
- 99900524804101842
- Language
- English
- Resource Type
- Thesis