Adversarial Learning of Poisson Factorisation Model for Gauging Brand Sentiment in User Reviews

In this paper, we propose the Brand-Topic Model (BTM) which aims to detect brandassociated polarity-bearing topics from product reviews. Different from existing models for sentiment-topic extraction which assume topics are grouped under discrete sentiment categories such as ‘positive’, ‘negative’ and ‘neural’, BTM is able to automatically infer real-valued brand-associated sentiment scores and generate fine-grained sentiment-topics in which we can observe continuous changes of words under a certain topic (e.g., ‘shaver’ or ‘cream’) while its associated sentiment gradually varies from negative to positive. BTM is built on the Poisson factorisation model with the incorporation of adversarial learning. It has been evaluated on a dataset constructed from Amazon reviews. Experimental results show that BTM outperforms a number of competitive baselines in brand ranking, achieving a better balance of topic coherence and uniqueness, and extracting better-separated polaritybearing topics.

[1]  Feng Nan,et al.  Topic Modeling with Wasserstein Autoencoders , 2019, ACL.

[2]  Deyu Zhou,et al.  Neural Topic Modeling with Bidirectional Adversarial Training , 2020, ACL.

[3]  Xiang Li,et al.  Personalized Point-of-Interest Recommendation on Ranking with Poisson Factorization , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[4]  Ben Poole,et al.  Categorical Reparameterization with Gumbel-Softmax , 2016, ICLR.

[5]  Rui Wang,et al.  ATM: Adversarial-neural Topic Model , 2018, Inf. Process. Manag..

[6]  Lili Mou,et al.  Disentangled Representation Learning for Non-Parallel Text Style Transfer , 2018, ACL.

[7]  Pengtao Xie,et al.  Diversifying Restricted Boltzmann Machine for Document Modeling , 2015, KDD.

[8]  Deyu Zhou,et al.  Neural Topic Modeling with Cycle-Consistent Adversarial Training , 2020, EMNLP.

[9]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[10]  Ming-Syan Chen,et al.  Personalized Ranking on Poisson Factorization , 2018, SDM.

[11]  Yi Fang,et al.  Variational Deep Semantic Hashing for Text Documents , 2017, SIGIR.

[12]  Chuan Zhou,et al.  Collaborative Dynamic Sparse Topic Regression with User Profile Evolution for Item Recommendation , 2017, AAAI.

[13]  Michael I. Jordan,et al.  An Introduction to Variational Methods for Graphical Models , 1999, Machine Learning.

[14]  Michael Röder,et al.  Exploring the Space of Topic Coherence Measures , 2015, WSDM.

[15]  Atsuhiro Takasu,et al.  Adversarial Learning for Topic Models , 2018, ADMA.

[16]  Noah A. Smith,et al.  Neural Models for Documents with Metadata , 2017, ACL.

[17]  Adam E. Barry,et al.  Alcohol Advertising on Twitter—A Topic Model , 2018, American Journal of Health Education.

[18]  Michael I. Jordan,et al.  Graphical Models, Exponential Families, and Variational Inference , 2008, Found. Trends Mach. Learn..

[19]  Haoran Xie,et al.  Siamese Network-Based Supervised Topic Modeling , 2018, EMNLP.

[20]  Eric P. Xing,et al.  Dynamic Topic Modeling for Monitoring Market Competition from Online Text and Image Data , 2015, KDD.

[21]  Xin Wang,et al.  Understanding Users' Budgets for Recommendation with Hierarchical Poisson Factorization , 2017, IJCAI.

[22]  Sebastian Nowozin,et al.  Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations , 2017, AAAI.

[23]  Zhe Gan,et al.  Scalable Deep Poisson Factor Analysis for Topic Modeling , 2015, ICML.

[24]  Yanchun Zhang,et al.  A Topic Model Based on Poisson Decomposition , 2017, CIKM.

[25]  Julian J. McAuley,et al.  Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering , 2016, WWW.

[26]  I JordanMichael,et al.  Graphical Models, Exponential Families, and Variational Inference , 2008 .

[27]  Timothy Baldwin,et al.  Automatic Labelling of Topics with Neural Embeddings , 2016, COLING.

[28]  Naonori Ueda,et al.  Topic Tracking Model for Analyzing Consumer Purchase Behavior , 2009, IJCAI.

[29]  Ole Winther,et al.  Ladder Variational Autoencoders , 2016, NIPS.

[30]  David M. Blei,et al.  Variational Inference: A Review for Statisticians , 2016, ArXiv.

[31]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[32]  Ruifeng Xu,et al.  Multi-Task Mutual Learning for Joint Sentiment Classification and Topic Detection , 2020 .

[33]  Hwee Tou Ng,et al.  An Unsupervised Neural Attention Model for Aspect Extraction , 2017, ACL.

[34]  Marcus Rohrbach,et al.  Decoupling Representation and Classifier for Long-Tailed Recognition , 2020, ICLR.

[35]  Gabriel Doyle.  Financial Topic Models , 2009 .

[36]  Charles A. Sutton,et al.  Autoencoding Variational Inference For Topic Models , 2017, ICLR.

[37]  Heri Ramampiaro,et al.  Content-Based Social Recommendation with Poisson Matrix Factorization , 2017, ECML/PKDD.

[38]  David M. Blei,et al.  Text-Based Ideal Points , 2020, ACL.

[39]  Hwee Tou Ng,et al.  Effective Attention Modeling for Aspect-Level Sentiment Classification , 2018, COLING.