Paper
11 October 2023 A study of keyword extraction for short news documents
Lingfei Li, Yueshan Wang, Xiaoyi Zhang
Author Affiliations +
Proceedings Volume 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023); 128004H (2023) https://doi.org/10.1117/12.3003835
Event: 6th International Conference on Computer Information Science and Application Technology (CISAT 2023), 2023, Hangzhou, China
Abstract
In the network age, a large number of news with uneven quality has become a problem of information circulation. People lack energy to distinguish the quality of news, so there is a higher demand for keyword extraction technology. In this paper, the sliding window-based LTFIDF_POS algorithm is proposed for the keyword extraction problem of short news texts without labels. Firstly, the TF-IDF algorithm is improved by using sliding window, lexical information as well as word position information based on a normal distribution function. Then the LTFIDF_POS algorithm is given by fusing the three improved methods together. It fully considers the unknown words and the distribution information of words in the text, and the experiment results show that the algorithm is effective.
(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Lingfei Li, Yueshan Wang, and Xiaoyi Zhang "A study of keyword extraction for short news documents", Proc. SPIE 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023), 128004H (11 October 2023); https://doi.org/10.1117/12.3003835
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Windows

Statistical analysis

Education and training

Feature extraction

Mathematical optimization

Reflection

Statistical methods

RELATED CONTENT


Back to Top