แจ้งเอกสารไม่ครบถ้วน, ไม่ตรงกับชื่อเรื่อง หรือมีข้อผิดพลาดเกี่ยวกับเอกสาร ติดต่อที่นี่ ==>
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
Nattapong Sanchan. Mining users' intentions from Thai tweets using bert models. (). Mahanakorn University of Technology. Library. : , 2023.
Mining users' intentions from Thai tweets using bert models
Name: Nattapong Sanchan
Address:
Bangkok University.School of information technology and innovation
keyword:
Intent mining
Abstract:
In this paper, we explore the mining of users' intentions in text. We viewed that being able to identify the intentions of users expressed in textual data provides us to specifically know aims and what users want to do. In the experiment, we collected tweets, constructed a Thai intention corpus, and performed a binary classification tesk on the corpus. We investigated the intent classification results derived through the application of 3 different bidirectional encoder repressentations from transformers (BERT), Word embedding, and bag of words models. The results revealed that BERT based EN-TH cased model outperforms other models in both classification and processing time aspects. It achieves the F1 score of 0.81 and performs the classification tesk faster than other BERT models up to 15%.
Mahanakorn University of Technology. Library
Address:
BANGKOK
Email:
mutelibrary@gmail.com
Created:
2023
Modified:
2023-11-07
Issued:
2023-11-07
บทความ/Article
application/pdf
BibliograpyCitation :
Journal of information science and technology Vol. 13, no.1 Jan-Jun 2023, p. 17-25
eng
©copyrights Mahanakorn University of Technology
RightsAccess:
ใช้เวลา
0.038693 วินาที
Nattapong Sanchan
| Title | Contributor | Type |
|---|---|---|
| Mining users' intentions from Thai tweets using bert models
มหาวิทยาลัยเทคโนโลยีมหานคร Nattapong Sanchan | บทความ/Article |