Multi Task Mutual Learning for Joint Sentiment Classification and Topic Detection

TY - JOUR

T1 - Multi Task Mutual Learning for Joint Sentiment Classification and Topic Detection

AU - Gui, Lin

AU - Jia, Leng

AU - Zhou, Jiyun

AU - Xu, Ruifeng

AU - He, Yulan

PY - 2022/4/1

Y1 - 2022/4/1

N2 - Recently, advances in neural network approaches have achieved many successes in both sentiment classification and probabilistic topic modeling. On the one hand, latent topics derived from the global context of documents could be helpful in capturing more accurate word semantics and hence could potentially improve the sentiment classification accuracy. On the other hand, the word-level attention vectors obtained during the learning of sentiment classifiers could carry word-level polarity information and can be used to guide the discovery of topics in topic modeling. This paper proposes a multi-task learning framework which jointly learns a sentiment classifier and a topic model by making the word-level latent topic distributions in the topic model to be similar to the word-level attention vectors in sentiment classifiers through mutual learning. Experimental results on the Yelp and IMDB datasets verify the superior performance of the proposed framework over strong baselines on both sentiment classification and topic modeling. The proposed framework also extracts more interpretable topics compared to other conventional topic models and neural topic models.

AB - Recently, advances in neural network approaches have achieved many successes in both sentiment classification and probabilistic topic modeling. On the one hand, latent topics derived from the global context of documents could be helpful in capturing more accurate word semantics and hence could potentially improve the sentiment classification accuracy. On the other hand, the word-level attention vectors obtained during the learning of sentiment classifiers could carry word-level polarity information and can be used to guide the discovery of topics in topic modeling. This paper proposes a multi-task learning framework which jointly learns a sentiment classifier and a topic model by making the word-level latent topic distributions in the topic model to be similar to the word-level attention vectors in sentiment classifiers through mutual learning. Experimental results on the Yelp and IMDB datasets verify the superior performance of the proposed framework over strong baselines on both sentiment classification and topic modeling. The proposed framework also extracts more interpretable topics compared to other conventional topic models and neural topic models.

KW - Task analysis

KW - Artificial neural networks

KW - Training

KW - Probabilistic logic

KW - Semantics

KW - Context modeling

KW - Multi-task learning

KW - sentiment analysis

KW - neural topic models

UR - http://www.scopus.com/inward/record.url?scp=85126539606&partnerID=8YFLogxK

U2 - 10.1109/TKDE.2020.2999489

DO - 10.1109/TKDE.2020.2999489

M3 - Article

SN - 1041-4347

VL - 34

SP - 1915

EP - 1927

JO - IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING

JF - IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING

IS - 4

ER -