intelligent database systems lab presenter : jian-ren chen authors : ahmed abbasi, stephen france,...

22
Intelligent Database Systems Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011 , IEEE TKDE Selecting Attributes for Sentiment Classification Using Feature Relation Networks

Upload: laurence-watson

Post on 17-Dec-2015

216 views

Category:

Documents


1 download

TRANSCRIPT

Page 1: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Presenter : JIAN-REN CHEN

Authors : Ahmed Abbasi, Stephen France, Zhu Zhang,

     and Hsinchun Chen

2011 , IEEE TKDE

Selecting Attributes for Sentiment Classification Using Feature Relation Networks

Page 2: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Outlines

MotivationObjectivesMethodologyExperimentsConclusionsComments

Page 3: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

MotivationSentiment analysis has emerged as a method for

mining opinions from such text archives.

challenging problem:

1. requires the use of large quantities of linguistic features

2. integrate these heterogeneous n-gram categories into a single

feature set

- noise 、 redundancy and computational limitations

1) polarity 2) intensityI don’t like you 、 I hate you

Page 4: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

n-gram - (Markov model)天氣:晴天、陰天、雨天

美麗 vs 美痢

“HAPAX” and “DIS” tagsI hate Jimreplaced with “I hate HAPAX”

Page 5: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Objectives• Feature Relation Network (FRN) considers semantic information

and also leverages the syntactic relationships between n-gram

features.

- enhanced sentiment classification on extended sets of

heterogeneous n-gram features.

Page 6: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Methodology-Extended N-Gram Feature Set

Page 7: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Methodology - Subsumption Relations

A subsumes B(A → B) “I love chocolate”

  unigram :   I, LOVE, CHOCOLATE  bigrams :   I LOVE, LOVE CHOCOLATE  trigrams :   I LOVE CHOCOLATE

W hat about the bigrams and trigrams?

It depends on their weight.Their weight exceeds that of their general lower order counterparts by threshold t.

Page 8: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Methodology - Parallel RelationsA parallel B (A - B)

POS tag: “ADMIRE_VP”   → “ like”     semantic class: “SYN-Affection”  → “ love”

A and B have a correlation coefficient greater than some threshold p, one of the attributes is removed to avoid redundancy.

Page 9: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Methodology - The Complete Network

Page 10: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Methodology - Incorporating Semantic  Information

Page 11: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Experiments - Datasets

Page 12: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Experiments – FRN vs Univariate

Page 13: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Experiments - FRN vs Univariate (WithinOne)

Page 14: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Experiments - FRN vs Multivariate

Page 15: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Experiments - FRN vs Multivariate (WithinOne)

Page 16: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Experiments - FRN vs Hybrid

Page 17: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Experiments - FRN vs Hybrid (WithinOne)

Page 18: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Experiments - Ablation

Page 19: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Experiments - Parametert (0.0005, 0.005, 0.05, and 0.5)p (0.80, 0.90, and 1.00)

Page 20: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Experiments - Average Runtimes

Page 21: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Conclusions

• FRN had significantly higher best accuracy and best

percentage within-one across three testbeds.

• The ablation and parameter testing results play an

important role for the subsumption and parallel

relation thresholds.

Page 22: Intelligent Database Systems Lab Presenter : JIAN-REN CHEN Authors : Ahmed Abbasi, Stephen France, Zhu Zhang, and Hsinchun Chen 2011, IEEE TKDE Selecting

Intelligent Database Systems Lab

Comments• Advantages

- accuracy 、 computationally efficient• Disadvantage

- ablation and parameter is sensitive• Applications

- sentiment classification- feature selection method