Personalized Sentiment classification based on latent individuality of microblog users

Kaisong Song, Shi Feng, Wei Gao, Daling Wang, Ge Yu, Kam Fai Wong

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Sentiment expression in microblog posts often reflects user’s specific individuality due to different language habit, personal character, opinion bias and so on. Existing sentiment classification algorithms largely ignore such latent personal distinctions among different microblog users. Meanwhile, sentiment data of microblogs are sparse for individual users, making it infeasible to learn effective personalized classifier. In this chapter, we describe a novel, extensible personalized sentiment classification method based on a variant of latent factor model to capture personal sentiment variations by mapping users and posts into a low-dimensional factor space. We alleviate the sparsity of personal texts by decomposing the posts into words which are further represented by the weighted sentiment and topic units based on a set of syntactic units of words obtained from dependency parsing results. To strengthen the representation of users, we leverage users following relation to consolidate the individuality of a user fused from other users with similar interests. Results on real-world microblog datasets confirm that our method outperforms state-of-the-art baseline algorithms with large margins.

Original languageEnglish
Title of host publicationSocial Media Content Analysis
Subtitle of host publicationNatural Language Processing and Beyond
PublisherWorld Scientific Publishing Co. Pte Ltd
Pages197-214
Number of pages18
ISBN (Electronic)9789813223615
ISBN (Print)9789813223608
DOIs
Publication statusPublished - 1 Jan 2017

Fingerprint

Syntactics
Classifiers

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Song, K., Feng, S., Gao, W., Wang, D., Yu, G., & Wong, K. F. (2017). Personalized Sentiment classification based on latent individuality of microblog users. In Social Media Content Analysis: Natural Language Processing and Beyond (pp. 197-214). World Scientific Publishing Co. Pte Ltd. https://doi.org/10.1142/9789813223615_0014

Personalized Sentiment classification based on latent individuality of microblog users. / Song, Kaisong; Feng, Shi; Gao, Wei; Wang, Daling; Yu, Ge; Wong, Kam Fai.

Social Media Content Analysis: Natural Language Processing and Beyond. World Scientific Publishing Co. Pte Ltd, 2017. p. 197-214.

Research output: Chapter in Book/Report/Conference proceedingChapter

Song, K, Feng, S, Gao, W, Wang, D, Yu, G & Wong, KF 2017, Personalized Sentiment classification based on latent individuality of microblog users. in Social Media Content Analysis: Natural Language Processing and Beyond. World Scientific Publishing Co. Pte Ltd, pp. 197-214. https://doi.org/10.1142/9789813223615_0014
Song K, Feng S, Gao W, Wang D, Yu G, Wong KF. Personalized Sentiment classification based on latent individuality of microblog users. In Social Media Content Analysis: Natural Language Processing and Beyond. World Scientific Publishing Co. Pte Ltd. 2017. p. 197-214 https://doi.org/10.1142/9789813223615_0014
Song, Kaisong ; Feng, Shi ; Gao, Wei ; Wang, Daling ; Yu, Ge ; Wong, Kam Fai. / Personalized Sentiment classification based on latent individuality of microblog users. Social Media Content Analysis: Natural Language Processing and Beyond. World Scientific Publishing Co. Pte Ltd, 2017. pp. 197-214
@inbook{8bbc3b781a464c70a8f1908f03b1f446,
title = "Personalized Sentiment classification based on latent individuality of microblog users",
abstract = "Sentiment expression in microblog posts often reflects user’s specific individuality due to different language habit, personal character, opinion bias and so on. Existing sentiment classification algorithms largely ignore such latent personal distinctions among different microblog users. Meanwhile, sentiment data of microblogs are sparse for individual users, making it infeasible to learn effective personalized classifier. In this chapter, we describe a novel, extensible personalized sentiment classification method based on a variant of latent factor model to capture personal sentiment variations by mapping users and posts into a low-dimensional factor space. We alleviate the sparsity of personal texts by decomposing the posts into words which are further represented by the weighted sentiment and topic units based on a set of syntactic units of words obtained from dependency parsing results. To strengthen the representation of users, we leverage users following relation to consolidate the individuality of a user fused from other users with similar interests. Results on real-world microblog datasets confirm that our method outperforms state-of-the-art baseline algorithms with large margins.",
author = "Kaisong Song and Shi Feng and Wei Gao and Daling Wang and Ge Yu and Wong, {Kam Fai}",
year = "2017",
month = "1",
day = "1",
doi = "10.1142/9789813223615_0014",
language = "English",
isbn = "9789813223608",
pages = "197--214",
booktitle = "Social Media Content Analysis",
publisher = "World Scientific Publishing Co. Pte Ltd",
address = "Singapore",

}

TY - CHAP

T1 - Personalized Sentiment classification based on latent individuality of microblog users

AU - Song, Kaisong

AU - Feng, Shi

AU - Gao, Wei

AU - Wang, Daling

AU - Yu, Ge

AU - Wong, Kam Fai

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Sentiment expression in microblog posts often reflects user’s specific individuality due to different language habit, personal character, opinion bias and so on. Existing sentiment classification algorithms largely ignore such latent personal distinctions among different microblog users. Meanwhile, sentiment data of microblogs are sparse for individual users, making it infeasible to learn effective personalized classifier. In this chapter, we describe a novel, extensible personalized sentiment classification method based on a variant of latent factor model to capture personal sentiment variations by mapping users and posts into a low-dimensional factor space. We alleviate the sparsity of personal texts by decomposing the posts into words which are further represented by the weighted sentiment and topic units based on a set of syntactic units of words obtained from dependency parsing results. To strengthen the representation of users, we leverage users following relation to consolidate the individuality of a user fused from other users with similar interests. Results on real-world microblog datasets confirm that our method outperforms state-of-the-art baseline algorithms with large margins.

AB - Sentiment expression in microblog posts often reflects user’s specific individuality due to different language habit, personal character, opinion bias and so on. Existing sentiment classification algorithms largely ignore such latent personal distinctions among different microblog users. Meanwhile, sentiment data of microblogs are sparse for individual users, making it infeasible to learn effective personalized classifier. In this chapter, we describe a novel, extensible personalized sentiment classification method based on a variant of latent factor model to capture personal sentiment variations by mapping users and posts into a low-dimensional factor space. We alleviate the sparsity of personal texts by decomposing the posts into words which are further represented by the weighted sentiment and topic units based on a set of syntactic units of words obtained from dependency parsing results. To strengthen the representation of users, we leverage users following relation to consolidate the individuality of a user fused from other users with similar interests. Results on real-world microblog datasets confirm that our method outperforms state-of-the-art baseline algorithms with large margins.

UR - http://www.scopus.com/inward/record.url?scp=85041571472&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041571472&partnerID=8YFLogxK

U2 - 10.1142/9789813223615_0014

DO - 10.1142/9789813223615_0014

M3 - Chapter

SN - 9789813223608

SP - 197

EP - 214

BT - Social Media Content Analysis

PB - World Scientific Publishing Co. Pte Ltd

ER -