Clustering Short-Text Using Non-negative Matrix Factorization of Hadamard Product of Similarities

2013 ◽  
pp. 145-155 ◽  
Author(s):  
Krutika Verma ◽  
Mukesh K. Jadon ◽  
Arun K. Pujari
Keyword(s):  
Matrix Factorization ◽  
Hadamard Product ◽  
Short Text ◽  
Non Negative Matrix Factorization

scholarly journals Topic Subject Creation Using Unsupervised Learning for Topic Modeling

2020 ◽  
Vol 13 (3) ◽  
pp. 57
Author(s):  
Rashid Mehdiyev ◽  
Jean Nava ◽  
Karan Sodhi ◽  
Saurav Acharya ◽  
Annie Ibrahim Rana
Keyword(s):  
Matrix Factorization ◽  
Call Center ◽  
Latent Dirichlet Allocation ◽  
Text Data ◽  
Short Text ◽  
Novel Method ◽  
The Subject ◽  
Mining Algorithms ◽  
Topic Mining ◽  
Non Negative Matrix Factorization

We address the problem of topic mining and labelling in the domain of retail customer communications to summarize the subject of customers inquiries. The performance of two popular topic mining algorithms - Non-Negative Matrix Factorization (NMF) and Latent Dirichlet Allocation (LDA) – were compared, and a novel method to assign topic subject labels to the customer inquiries in an automated way was proposed. Experiments using a retailer’s call center data verify the efficacy and efficiency of the proposed topic labelling algorithm. Furthermore, the evaluation of results from both the algorithms seems to indicate the preference of using Non-Negative Matrix Factorization applied to short text data.

Sign in / Sign up

Export Citation Format

Share Document