| Issue |
E3S Web Conf.
Volume 460, 2023
International Scientific Conference on Biotechnology and Food Technology (BFT-2023)
|
|
|---|---|---|
| Article Number | 04027 | |
| Number of page(s) | 6 | |
| Section | IoT, Big Data and AI in Food Industry | |
| DOI | https://doi.org/10.1051/e3sconf/202346004027 | |
| Published online | 11 December 2023 | |
A mathematical modification of the WNTM associative algorithm for cognitive analysis and efficient detection of dualisms in text and video streaming data
T.F. Gorbachev Kuzbass State Technical University, 28 Vesennya st., 650000 Kemerovo, Russian Federation
* Corresponding author: pylovpa@kuzstu.ru
We report on a modification of the WNTM (Word Network Topic Model) algorithm for efficient modelling of bitermes – pairs of words that frequently occur together in texts of different topics. The modified algorithm is an extension of the classical topic model and allows efficient detection and extraction of semantic relations between pairs of words. The paper presents formalized mathematical equations describing the process of modelling biterms, and also presents the results of experiments on real text data, confirming the effectiveness of the proposed approach.
© The Authors, published by EDP Sciences, 2023
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.