Advanced Hierarchical Topic Labeling for Short Text

Show simple item record

dc.contributor.author TIWARI, PARAS
dc.date.accessioned 2024-02-01T07:34:38Z
dc.date.available 2024-02-01T07:34:38Z
dc.date.issued 2023-04-05
dc.identifier.issn 21693536
dc.identifier.uri http://localhost:8080/xmlui/handle/123456789/2757
dc.description This paper published with affiliation IIT (BHU), Varanasi in Open Access Mode. en_US
dc.description.abstract Hierarchical Topic Modeling is the probabilistic approach for discovering latent topics distributed hierarchically among the documents. The distributed topics are represented with the respective topic terms. An unambiguous conclusion from the topic term distribution is a challenge for readers. The hierarchical topic labeling eases the challenge by facilitating an individual, appropriate label for each topic at every level. In this work, we propose a BERT-embedding inspired methodology for labeling hierarchical topics in short text corpora. The short texts have gained significant popularity on multiple platforms in diverse domains. The limited information available in the short text makes it difficult to deal with. In our work, we have used three diverse short text datasets that include both structured and unstructured instances. Such diversity ensures the broad application scope of this work. Considering the relevancy factor of the labels, the proposed methodology has been compared against both automatic and human annotators. Our proposed methodology outperformed the benchmark with an average score of 0.4185, 49.50, and 49.16 for cosine similarity, exact match, and partial match, respectively. en_US
dc.language.iso en en_US
dc.publisher Institute of Electrical and Electronics Engineers Inc. en_US
dc.relation.ispartofseries IEEE Access;11
dc.subject Document categorization en_US
dc.subject hierarchical topic labeling en_US
dc.subject hierarchical topic modeling en_US
dc.subject topic labeling en_US
dc.subject topic modeling en_US
dc.title Advanced Hierarchical Topic Labeling for Short Text en_US
dc.type Article en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search in IDR


Advanced Search

Browse

My Account