Abstract
Communicating in short messages, such as using microblogs, was becoming more popular currently. Twitter https://twitter.com supports microblogs and retrieval of the blogs by users. To retrieve Twitter documents, we need specific strategies due to its specific characteristics. One new strategy for improving the effectiveness of twitter document retrieval is using the query expansion technique. This paper elaborates query expansion in twitter document retrieval by using the hashtag. We compared the effectiveness of query expansion in four different scenarios: the baseline result using no query expansion, highest scoredterm in terms of frequency-inverse document frequency (tfidf), maximum hashtag occurance, and combination of the highest scored-term and the maximum hashtag. The results show that the combination of the maximum term in tfidf and the maximum hashtag performs better in retrieving relevant documents than the baseline.
Highlights
Microblog, like Twitter, has emerged and become a popular social media to communicate short messages
We focus on our proposed methods: the maximum term in term frequency inverse-document frequency, the maximum hashtag, and the combination of both
In the formula, ft indicates the frequency of a term and Di represents the ith document in which term t is computed. idf is Inverse Document Frequency which is the number of documents that contain the investigated term divided by the total number of documents in the collection
Summary
Like Twitter, has emerged and become a popular social media to communicate short messages. Twitter has some specific characteristics which differs from regular text: time sensitivity, short length, unstructured phrases and abundant information, as described in Received: 20 January 2016 Accepted: 12 September 2016. The short length characteristics on Twitter are represented by only allowing a maximum of 140 characters each. This short text often yields less relevance of retrieved documents. A number of methods have been developed for improving the performance of twitter relevant document retrieval, and researches on query expansion have been conducted for many years for this purpose. This paper concentrates on using the local methods of query expansion by employing hashtag
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Journal of Information and Communication Technology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
