Titlebar

Export bibliographic data
Literature by the same author
plus on the publication server
plus at Google Scholar

 

Embedding Semantic Anchors to Guide Topic Models on Short Text Corpora

Title data

Steuber, Florian ; Schneider, Sinclair ; Schönfeld, Mirco:
Embedding Semantic Anchors to Guide Topic Models on Short Text Corpora.
In: Big Data Research. Vol. 27 (28 February 2022) . - No. 100293.
ISSN 2214-5796
DOI: https://doi.org/10.1016/j.bdr.2021.100293

Project information

Project title:
Project's official titleProject's id
Africa Multiple Cluster of Excellence at the University of BayreuthEXC 2052/1 – 390713894

Project financing: Deutsche Forschungsgemeinschaft

Abstract in another language

Documents on the social media platform Twitter are formulated in short and simple style, instead of being written extensively and elaborately. Further, the core message of a post is often encoded into characteristic phrases called hashtags. These hashtags illustrate the semantics of a post or tie it to a specific topic. In this paper, we propose multiple approaches of using hashtags and their surrounding texts to improve topic modeling of short texts. We use transfer learning by applying a pre-trained word embedding of hashtags to derive preliminary topics. These function as supervising information, or seed topics and are passed to Archetypal LDA (A-LDA), a recent variant of Latent Dirichlet Allocation. We demonstrate the effectiveness of our approach using a large corpus of posts exemplarily on Twitter. Our approaches improve the topic model's qualities in terms of various quantitative metrics. Moreover, the presented algorithms used to extract seed topics can be utilized as form of lightweight topic model by themselves. Hence, our approaches create additional analytical opportunities and can help to gain a more detailed understanding of what people are talking about on social media. By using big data in terms of millions of tweets for preprocessing and fine-tuning, we enable the classification algorithm to produce topics that are very coherent to the reader.

Further data

Item Type: Article in a journal
Refereed: Yes
Keywords: Topic modeling; Short text; Word embedding; Transfer learning; Big data
Institutions of the University: Faculties > Faculty of Languages and Literature
Faculties > Faculty of Languages and Literature > Juniorprofessur Datenmodellierung und interdisziplinäre Wissensgenerierung
Faculties > Faculty of Languages and Literature > Juniorprofessur Datenmodellierung und interdisziplinäre Wissensgenerierung > Juniorprofessur Datenmodellierung und interdisziplinäre Wissensgenerierung - Juniorprof. Dr. Mirco Schönfeld
Result of work at the UBT: Yes
DDC Subjects: 000 Computer Science, information, general works > 004 Computer science
Date Deposited: 18 Nov 2021 09:38
Last Modified: 18 Nov 2021 09:38
URI: https://eref.uni-bayreuth.de/id/eprint/67879