Ronran, Chirawan and Unankard, Sayan and Nadee, Wanvimol and Khomwichai, Nongkran and Sirirangsi, Rangsit (2016) Thai word segmentation on social networks with time sensitivity. In: Knowledge Management International Conference (KMICe) 2016, 29 – 30 August 2016, Chiang Mai, Thailand.

Preview

PDF Download (723kB) | Preview

Abstract

Social network service like Twitter is one of the important social networks that has had a huge impact on Thai culture.It has changed the behavior of many Thai people from using televisions to using computers or smart phones regularly.Thai people also share their experiences and get information such as news on social networks. With the increasing number of micro-blog messages that are originated and discussed over social networks, Thai word segmentation is becoming a compelling research issue as it is an important task in natural language processing. However, the existing Thai segmentation approaches are not designed to deal with short and noisy messages like Twitter. In this paper, we proposed Thai word segmentation on social networks approach by exploit both the local context (in tweets) and the global context from Thai Wikipedia.We evaluate our approach based on a real-world Twitter dataset. Our experiments show that the proposed approach can effectively segment Twitter messages over the baseline.

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	ISBN: 978-967-0910-19-2 Organized by: College of Arts and Sciences, Universiti Utara Malaysia
Uncontrolled Keywords:	Thai Segmentation, Tokenization, Social Network, Time Sensitivity.
Subjects:	T Technology > T Technology (General)
Divisions:	School of Computing
Depositing User:	Mrs. Norazmilah Yaakub
Date Deposited:	30 Nov 2016 08:12
Last Modified:	30 Nov 2016 08:12
URI:	https://repo.uum.edu.my/id/eprint/20123

Actions (login required)

View Item