Emerging Research Topic Detection Using Filtered-LDA

Comparing two sets of documents to identify new topics is useful in many applications, like discovering trending topics from sets of scientific papers, emerging topic detection in microblogs, and interpreting sentiment variations in Twitter. In this paper, the main topic-modeling-based approaches to...

Full description

Saved in:
Bibliographic Details
Main Author: Alattar, Fuad (author)
Other Authors: Shaalan, Khaled (author)
Published: 2021
Subjects:
Online Access:https://bspace.buid.ac.ae/handle/1234/2987
https://doi.org/10.3390/ai2040035.
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1862980619815878656
author Alattar, Fuad
author2 Shaalan, Khaled
author2_role author
author_facet Alattar, Fuad
Shaalan, Khaled
author_role author
dc.creator.none.fl_str_mv Alattar, Fuad
Shaalan, Khaled
dc.date.none.fl_str_mv 2021
2025-05-13T13:20:05Z
2025-05-13T13:20:05Z
dc.identifier.none.fl_str_mv Alattar, F. and Shaalan, K. (2021) “Emerging Research Topic Detection Using Filtered-LDA,” AI, 2(4), pp. 578–599.
2673-2688
https://bspace.buid.ac.ae/handle/1234/2987
https://doi.org/10.3390/ai2040035.
dc.language.none.fl_str_mv en
dc.publisher.none.fl_str_mv MDPI
dc.relation.none.fl_str_mv AIv2 n4 (20211031): 578-599
dc.subject.none.fl_str_mv emerging topic detection; research trend detection; topic discovery; topic modeling; hot topics; trending topics; FB-LDA; Filtered-LDA
dc.title.none.fl_str_mv Emerging Research Topic Detection Using Filtered-LDA
dc.type.none.fl_str_mv Article
description Comparing two sets of documents to identify new topics is useful in many applications, like discovering trending topics from sets of scientific papers, emerging topic detection in microblogs, and interpreting sentiment variations in Twitter. In this paper, the main topic-modeling-based approaches to address this task are examined to identify limitations and necessary enhancements. To overcome these limitations, we introduce two separate frameworks to discover emerging topics through a filtered latent Dirichlet allocation (filtered-LDA) model. The model acts as a filter that identifies old topics from a timestamped set of documents, removes all documents that focus on old topics, and keeps documents that discuss new topics. Filtered-LDA also genuinely reduces the chance of using keywords from old topics to represent emerging topics. The final stage of the filter uses multiple topic visualization formats to improve human interpretability of the filtered topics, and it presents the most-representative document for each topic.
id budr_e57d8e321663dc1cc2d7ee888d8d6fbe
identifier_str_mv Alattar, F. and Shaalan, K. (2021) “Emerging Research Topic Detection Using Filtered-LDA,” AI, 2(4), pp. 578–599.
2673-2688
language_invalid_str_mv en
network_acronym_str budr
network_name_str The British University in Dubai repository
oai_identifier_str oai:bspace.buid.ac.ae:1234/2987
publishDate 2021
publisher.none.fl_str_mv MDPI
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Emerging Research Topic Detection Using Filtered-LDAAlattar, FuadShaalan, Khaledemerging topic detection; research trend detection; topic discovery; topic modeling; hot topics; trending topics; FB-LDA; Filtered-LDAComparing two sets of documents to identify new topics is useful in many applications, like discovering trending topics from sets of scientific papers, emerging topic detection in microblogs, and interpreting sentiment variations in Twitter. In this paper, the main topic-modeling-based approaches to address this task are examined to identify limitations and necessary enhancements. To overcome these limitations, we introduce two separate frameworks to discover emerging topics through a filtered latent Dirichlet allocation (filtered-LDA) model. The model acts as a filter that identifies old topics from a timestamped set of documents, removes all documents that focus on old topics, and keeps documents that discuss new topics. Filtered-LDA also genuinely reduces the chance of using keywords from old topics to represent emerging topics. The final stage of the filter uses multiple topic visualization formats to improve human interpretability of the filtered topics, and it presents the most-representative document for each topic.MDPI2025-05-13T13:20:05Z2025-05-13T13:20:05Z2021ArticleAlattar, F. and Shaalan, K. (2021) “Emerging Research Topic Detection Using Filtered-LDA,” AI, 2(4), pp. 578–599.2673-2688https://bspace.buid.ac.ae/handle/1234/2987https://doi.org/10.3390/ai2040035.enAIv2 n4 (20211031): 578-599oai:bspace.buid.ac.ae:1234/29872025-05-13T13:30:50Z
spellingShingle Emerging Research Topic Detection Using Filtered-LDA
Alattar, Fuad
emerging topic detection; research trend detection; topic discovery; topic modeling; hot topics; trending topics; FB-LDA; Filtered-LDA
title Emerging Research Topic Detection Using Filtered-LDA
title_full Emerging Research Topic Detection Using Filtered-LDA
title_fullStr Emerging Research Topic Detection Using Filtered-LDA
title_full_unstemmed Emerging Research Topic Detection Using Filtered-LDA
title_short Emerging Research Topic Detection Using Filtered-LDA
title_sort Emerging Research Topic Detection Using Filtered-LDA
topic emerging topic detection; research trend detection; topic discovery; topic modeling; hot topics; trending topics; FB-LDA; Filtered-LDA
url https://bspace.buid.ac.ae/handle/1234/2987
https://doi.org/10.3390/ai2040035.