Sentiment Classification Using Word Sub-sequences and Dependency Sub-trees

Matsumoto, Shotaro; Takamura, Hiroya; Okumura, Manabu

doi:10.1007/11430919_37

Cited by 148 publications

(88 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, the sentences of a new review are classified based on the highest-ranking matching pattern. This is in contrast to the work in [16], which treats dependency tree patterns as features in an SVM classifier.…”

Section: Introductionmentioning

confidence: 85%

“…Matsumoto et al [16] is the closest work to our proposed method, which we experimentally compare in the Results section. They extract frequent word sub-sequences and dependency subtrees from the training data and use them as features in an SVM sentiment classifier.…”

Section: Sentiment Analysis With Dependency Treesmentioning

confidence: 99%

“…Matsumoto: We implemented the method described in [16] using the best-performing combination of features from their experiment using the IMDB dataset from [32], i.e. unigrams, bigrams, frequent subsequences and lemmatized frequent subtrees.…”

Section: D2v-nnmentioning

confidence: 99%

“…Specifically, we consider an existing NLP-based classifier [16] and also propose a new one, which we refer as Dependency Tree-Based Classifier (DTC).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automatic Classification of Online Doctor Reviews: Evaluation of Text Classifier Algorithms (Preprint)

Rivas¹,

Montazeri²,

Le³

et al. 2018

Preprint

View full text Add to dashboard Cite

Background: An increasing number of doctor reviews are being generated by patients on the internet. These reviews address a diverse set of topics (features), including wait time, office staff, doctor's skills and bedside manner. Most previous work on automatic analysis of online customer reviews assumes that (a) product features are described unambiguously by a small number of keywords, e.g., "battery" for phones, and (b) the opinion for each feature has positive or negative sentiment. However, in the domain of doctor reviews, this setting is too restrictive: a feature such as "visit duration" for doctor reviews may be expressed in many ways, and does not necessarily have positive/negative sentiment.

show abstract

Section: Introductionmentioning

confidence: 85%

Section: Sentiment Analysis With Dependency Treesmentioning

confidence: 99%

Section: D2v-nnmentioning

confidence: 99%

“…Specifically, we consider an existing NLP-based classifier [16] and also propose a new one, which we refer as Dependency Tree-Based Classifier (DTC).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Classification of Online Doctor Reviews: Evaluation of Text Classifier Algorithms (Preprint)

Rivas¹,

Montazeri²,

Le³

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Most sentiment classification experiments were carried out by using Support Vector Machine (SVM) [12], Naive Bayes [18], Decision Trees [19], Maximum Entropy [20] and Conditional Random Fields (CRFs) [14]. The sentiment classification experiment implemented by [15] proved that CRFs classifiers outperform SVM classifiers.…”

Section: Related Workmentioning

confidence: 99%

Exploring the Importance of Modification Relation for Emotional Keywords Annotation and Emotion Types Recognition

Kita²,

Ren³

et al. 2011

IJIES

View full text Add to dashboard Cite

Abstract:In this study, we make a scheme to explore the importance of modification relation for the emotional keywords annotation and emotion types recognition. We extract three modification features which are degree words, negative words and conjunctions from the Chinese emotion corpus named Ren-CECps. Beside word and part-ofspeech, three modification relations are adopted as feature in this study. We have carried out eight experiments with different feature sets for emotional keywords annotation and emotion types recognition in sentence level. Eight basic emotion types have been selected and Conditional Random Fields have been employed as the algorithm. In the part of evaluation, we demonstrate the importance of the modification features and our experiment results show the effectiveness of the modification features for improving the performance of emotional keywords annotation and emotion types recognition.

show abstract

Sentiment Analysis in Social Media

Yusof

Lin

2017

Encyclopedia of Social Network Analysis and Mining

View full text Add to dashboard Cite

Sentiment Classification Using Word Sub-sequences and Dependency Sub-trees

Cited by 148 publications

References 7 publications

Automatic Classification of Online Doctor Reviews: Evaluation of Text Classifier Algorithms (Preprint)

Automatic Classification of Online Doctor Reviews: Evaluation of Text Classifier Algorithms (Preprint)

Exploring the Importance of Modification Relation for Emotional Keywords Annotation and Emotion Types Recognition

Sentiment Analysis in Social Media

Contact Info

Product

Resources

About