2 Matching Results

Search Results

Results: 1 - 2
open access

Automatic trend detection: Time-biased document clustering

Description: This article presents a novel approach of introducing a weighted temporal feature to bias a topic clustering toward articles in a similar time frame, performed over a set of finance journal abstracts from 1974 to 2020 to demonstrate how time can be emphasized in trend detection. The authors detect trending finance topics that are not identifiable when we use a standard clustering approach with no temporal bias.
Date: March 2, 2021
Creator: Behpour, Sahar; Mohammadi, Mohammadmahdi; Albert, Mark; Alam, Zinat S.; Wang, Lingling & Xiao, Ting
Item Type: Refine your search to only Article
Partner: University of North Texas
Back to Top of Screen