How Do I Look? Publicity Mining From Distributed Keyword Representation of Socially Infused News Articles

Yu-Lun Hsieh, Yung-Chun Chang, Chun-Han Chu, Wen-Lian Hsu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Previous work on opinion mining and sentiment analysis mainly concerns product, movie, or literature reviews; few applied this technique to analyze the publicity of person. We present a novel document modeling method that utilizes embeddings of emotion keywords to perform reader's emotion classification, and calculates a publicity score that serves as a quantifiable measure for the publicity of a person of interest. Experiments are conducted on two Chinese corpora that in total consists of over forty thousand users' emotional response after reading news articles. Results demonstrate that the proposed method can outperform state-of-the-art reader-emotion classification methods, and provide a substantial ground for publicity score estimation for candidates of political elections. We believe it is a promising direction for mining the publicity of a person from online social and news media that can be useful for propaganda and other purposes.
Original languageEnglish
Title of host publication The 4th International Workshop on Natural Language Processing for Social Media
Publication statusPublished - Nov 11 2016
Externally publishedYes

Fingerprint

Experiments

Cite this

Hsieh, Y-L., Chang, Y-C., Chu, C-H., & Hsu, W-L. (2016). How Do I Look? Publicity Mining From Distributed Keyword Representation of Socially Infused News Articles. In The 4th International Workshop on Natural Language Processing for Social Media The 4th International Workshop on Natural Language Processing for Social Media

How Do I Look? Publicity Mining From Distributed Keyword Representation of Socially Infused News Articles. / Hsieh, Yu-Lun; Chang, Yung-Chun; Chu, Chun-Han; Hsu, Wen-Lian.

The 4th International Workshop on Natural Language Processing for Social Media. 2016. (The 4th International Workshop on Natural Language Processing for Social Media).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hsieh, Y-L, Chang, Y-C, Chu, C-H & Hsu, W-L 2016, How Do I Look? Publicity Mining From Distributed Keyword Representation of Socially Infused News Articles. in The 4th International Workshop on Natural Language Processing for Social Media. The 4th International Workshop on Natural Language Processing for Social Media.
Hsieh Y-L, Chang Y-C, Chu C-H, Hsu W-L. How Do I Look? Publicity Mining From Distributed Keyword Representation of Socially Infused News Articles. In The 4th International Workshop on Natural Language Processing for Social Media. 2016. (The 4th International Workshop on Natural Language Processing for Social Media).
Hsieh, Yu-Lun ; Chang, Yung-Chun ; Chu, Chun-Han ; Hsu, Wen-Lian. / How Do I Look? Publicity Mining From Distributed Keyword Representation of Socially Infused News Articles. The 4th International Workshop on Natural Language Processing for Social Media. 2016. (The 4th International Workshop on Natural Language Processing for Social Media).
@inproceedings{fe23ae6d616c4aaa97e233b6f0eb6556,
title = "How Do I Look? Publicity Mining From Distributed Keyword Representation of Socially Infused News Articles",
abstract = "Previous work on opinion mining and sentiment analysis mainly concerns product, movie, or literature reviews; few applied this technique to analyze the publicity of person. We present a novel document modeling method that utilizes embeddings of emotion keywords to perform reader's emotion classification, and calculates a publicity score that serves as a quantifiable measure for the publicity of a person of interest. Experiments are conducted on two Chinese corpora that in total consists of over forty thousand users' emotional response after reading news articles. Results demonstrate that the proposed method can outperform state-of-the-art reader-emotion classification methods, and provide a substantial ground for publicity score estimation for candidates of political elections. We believe it is a promising direction for mining the publicity of a person from online social and news media that can be useful for propaganda and other purposes.",
author = "Yu-Lun Hsieh and Yung-Chun Chang and Chun-Han Chu and Wen-Lian Hsu",
year = "2016",
month = "11",
day = "11",
language = "English",
booktitle = "The 4th International Workshop on Natural Language Processing for Social Media",

}

TY - GEN

T1 - How Do I Look? Publicity Mining From Distributed Keyword Representation of Socially Infused News Articles

AU - Hsieh, Yu-Lun

AU - Chang, Yung-Chun

AU - Chu, Chun-Han

AU - Hsu, Wen-Lian

PY - 2016/11/11

Y1 - 2016/11/11

N2 - Previous work on opinion mining and sentiment analysis mainly concerns product, movie, or literature reviews; few applied this technique to analyze the publicity of person. We present a novel document modeling method that utilizes embeddings of emotion keywords to perform reader's emotion classification, and calculates a publicity score that serves as a quantifiable measure for the publicity of a person of interest. Experiments are conducted on two Chinese corpora that in total consists of over forty thousand users' emotional response after reading news articles. Results demonstrate that the proposed method can outperform state-of-the-art reader-emotion classification methods, and provide a substantial ground for publicity score estimation for candidates of political elections. We believe it is a promising direction for mining the publicity of a person from online social and news media that can be useful for propaganda and other purposes.

AB - Previous work on opinion mining and sentiment analysis mainly concerns product, movie, or literature reviews; few applied this technique to analyze the publicity of person. We present a novel document modeling method that utilizes embeddings of emotion keywords to perform reader's emotion classification, and calculates a publicity score that serves as a quantifiable measure for the publicity of a person of interest. Experiments are conducted on two Chinese corpora that in total consists of over forty thousand users' emotional response after reading news articles. Results demonstrate that the proposed method can outperform state-of-the-art reader-emotion classification methods, and provide a substantial ground for publicity score estimation for candidates of political elections. We believe it is a promising direction for mining the publicity of a person from online social and news media that can be useful for propaganda and other purposes.

M3 - Conference contribution

BT - The 4th International Workshop on Natural Language Processing for Social Media

ER -