Sentiment Classification User Modeling with Neural Network for - - PowerPoint PPT Presentation

User Behavior Analysis for Sentiment Classification

 User Modeling with Neural Network for Review Rating Prediction. Duyu Tang, Bing Qin, Ting Liu. IJCAI 2015, full paper.  Learning Semantic Representations of Users and Products for Document Level Sentiment Classification. Duyu Tang, Bing Qin, Ting Liu. ACL 2015, full paper.

1

Sentiment Classification

• Given a piece of text, the task aims to determine its

polarity as

• Positive / Negative
• 1-5 stars
• The task can be at
• Word/phrase level, sentence level, document level
• We target at document-level sentiment classification in

this work

2

Standard Supervised Learning Pipeline

Training Data Learning Algorithm Feature Representation Sentiment Classifier

3

Feature Learning Pipeline

Training Data Learning Algorithm Feature Representation Sentiment Classifier

Learn text representation/feature from data!

4

Deep Learning Pipeline

Training Data Learning Algorithm Feature Representation Sentiment Classifier Word Representation Words Semantic Composition

w1 w2 …… wn−1 wn

5

User Behavior is important for SA

• From a sentiment analysis perspective , users have

different habits to

• Assign ratings on IMDB, Yelp …
• Use diverse sentiment words to express one’s sentiment

User 1 User 2 Rating Histories Frequently used words good, ok, just soso, disgusting… awesome, amazing, excellent, not bad…

6

7

Softmax

gold rating = 2 w1 h1 h2 hn

Lookup Linear

……

Convolution Pooling

vd

Tanh

w2 wn

• Text semantics

The Approach

wi: word

The Approach

8

Softmax

gold rating = 2 w1 h1 Uk h2 hn

Lookup Linear

……

Convolution Pooling

vd

Tanh

× w2 Uk × wn Uk ×

• Text semantics
• +User-Text Associations

Uk: user wi: word The model in IJCAI 2015

The Approach

9

Softmax

gold rating = 2 w1 h1 Uk h2 hn

Lookup Linear

……

Convolution Pooling

vd

Tanh

× w2 Uk × wn Uk ×

• Text semantics
• +User-Text Associations
• +User-Sentiment Associations

Uk: user wi: word

uk

The Approach

10

Softmax

gold rating = 2 w1 h1 Uk Pj h2 hn

Lookup Linear

……

Convolution Pooling

uk pj vd

Tanh

w1 × × w2 Uk Pj w2 × × wn Uk Pj wn × ×

• Text semantics
• +User-Text Associations +Product-Text Associations
• +User-Sentiment Associations +Product-Sentiment

Pj: product Uk: user wi: word The model in ACL 2015

Experiments

• We conduct supervised learning on three datasets
• Some details
• We build the datasets by ourselves.
• Split each corpus into training, development

and testing sets with a 80/10/10 split

• IMBD is from Diao et al. 2014
• Yelp 2013 & 2014 come from Yelp Dataset Challenge

11

Experimental Results

• On IMDB dataset

12

Our Approach

Experimental Results

• On Yelp 2014 dataset

13

Our Approach

Experimental Results

• On Yelp 2013 dataset

14

Our Approach

In Summary

• We encode users (and products) in semantic vector

space, and apply them to sentiment classification.

• User and product representations can improve the

sentiment classification accuracy.

15

Thanks!

codes and resources will be publicly available at: http://ir.hit.edu.cn/~dytang

16