Topic extraction over danmaku text with pre-training model

Jing Yang; Xin Chen; Junchao Wu

doi:10.1117/12.3025823

8 April 2024 Topic extraction over danmaku text with pre-training model

Jing Yang, Xin Chen, Junchao Wu

Proceedings Volume 13090, International Conference on Computer Application and Information Security (ICCAIS 2023); 1309015 (2024) https://doi.org/10.1117/12.3025823
Event: International Conference on Computer Application and Information Security (ICCAIS 2023), 2023, Wuhan, China

Abstract

Topic extraction over danmaku is an important task due to the prevalence of danmaku text on the video website. Directly applying traditional topic models on danmaku text can’t work well. The underlying cause is that danmaku text is very short, unconventional and lacking explicit meaning. In this paper, an improved topic model that extends BTM is proposed to infer topics from danmaku text. The special steps in our method are that: (1) a pretraining model is trained on danmaku corpus to obtain word and sentence embeddings; (2) danmaku texts are clustered to generate distinct pseudo-danmaku texts; (3) biterms with the same or similar word pairs are removed from biterm set. Experimental results show that our method can improve the diversity among topics and find some special topic words.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Jing Yang, Xin Chen, and Junchao Wu "Topic extraction over danmaku text with pre-training model", Proc. SPIE 13090, International Conference on Computer Application and Information Security (ICCAIS 2023), 1309015 (8 April 2024); https://doi.org/10.1117/12.3025823

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available