Stability of topic modeling via matrix factorization

作者:

Highlights:

• The problem of the instability of standard topic modeling algorithms is investigated.

• Three new stability measures for topic models are proposed.

• Two new ensemble approaches for topic modeling with matrix factorization are proposed.

• A detailed evaluation of these approaches is performed on 10 text corpora.

摘要

•The problem of the instability of standard topic modeling algorithms is investigated.•Three new stability measures for topic models are proposed.•Two new ensemble approaches for topic modeling with matrix factorization are proposed.•A detailed evaluation of these approaches is performed on 10 text corpora.

论文关键词:Topic modeling,Topic stability,LDA,NMF

论文评审过程:Received 14 February 2017, Revised 11 August 2017, Accepted 28 August 2017, Available online 1 September 2017, Version of Record 7 September 2017.

论文官网地址:https://doi.org/10.1016/j.eswa.2017.08.047