Topic-Specific Stylistic Variations for Opinion Retrieval on Twitter

Anastasia Giachanou; Morgan Harvey; Fabio Crestani

doi:10.1007/978-3-319-30671-1_34

Topic-Specific Stylistic Variations for Opinion Retrieval on Twitter

Anastasia Giachanou, Morgan Harvey, Fabio Crestani

Computer Information Sciences Department

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

9 Citations (Scopus)

Abstract

Twitter has emerged as a popular platform for sharing information and expressing opinions. Twitter opinion retrieval is recognized as a powerful tool for finding people's attitudes on different topics. However, the vast amount of data and the informal language of tweets make opinion retrieval on Twitter very challenging. In this paper, we propose to leverage topic-specific stylistic variations to retrieve tweets that are both relevant and opinionated about a particular topic. Experimental results show that integrating topic specific textual meta-communications, such as emoticons and emphatic lengthening in a ranking function can significantly improve opinion retrieval performance on Twitter.

Original language	English
Title of host publication	Advances in Information Retrieval, 38th European Conference on IR Research, ECIR 2016
Editors	N. Ferro, F. Crestani, M.-F. Meons, J. Mothe, F. Silvestri, G. M. Di Nunzio, C. Hauff, G. Silvello
Place of Publication	London
Publisher	Springer
Pages	466-478
ISBN (Print)	978-3-319-30670-4
DOIs	https://doi.org/10.1007/978-3-319-30671-1_34
Publication status	Published - Apr 2016

Access to Document

10.1007/978-3-319-30671-1_34

Cite this

Giachanou, A., Harvey, M., & Crestani, F. (2016). Topic-Specific Stylistic Variations for Opinion Retrieval on Twitter. In N. Ferro, F. Crestani, M-F. Meons, J. Mothe, F. Silvestri, G. M. Di Nunzio, C. Hauff, & G. Silvello (Eds.), Advances in Information Retrieval, 38th European Conference on IR Research, ECIR 2016 (pp. 466-478). Springer. https://doi.org/10.1007/978-3-319-30671-1_34

@inbook{28b0a7a5de124212a20cfdae32acf6e8,

title = "Topic-Specific Stylistic Variations for Opinion Retrieval on Twitter",

abstract = "Twitter has emerged as a popular platform for sharing information and expressing opinions. Twitter opinion retrieval is recognized as a powerful tool for finding people's attitudes on different topics. However, the vast amount of data and the informal language of tweets make opinion retrieval on Twitter very challenging. In this paper, we propose to leverage topic-specific stylistic variations to retrieve tweets that are both relevant and opinionated about a particular topic. Experimental results show that integrating topic specific textual meta-communications, such as emoticons and emphatic lengthening in a ranking function can significantly improve opinion retrieval performance on Twitter.",

author = "Anastasia Giachanou and Morgan Harvey and Fabio Crestani",

year = "2016",

month = apr,

doi = "10.1007/978-3-319-30671-1_34",

language = "English",

isbn = "978-3-319-30670-4",

pages = "466--478",

editor = "N. Ferro and F. Crestani and M.-F. Meons and J. Mothe and F. Silvestri and {Di Nunzio}, {G. M.} and C. Hauff and G. Silvello",

booktitle = "Advances in Information Retrieval, 38th European Conference on IR Research, ECIR 2016",

publisher = "Springer",

address = "Germany",

}

Giachanou, A, Harvey, M & Crestani, F 2016, Topic-Specific Stylistic Variations for Opinion Retrieval on Twitter. in N Ferro, F Crestani, M-F Meons, J Mothe, F Silvestri, GM Di Nunzio, C Hauff & G Silvello (eds), Advances in Information Retrieval, 38th European Conference on IR Research, ECIR 2016. Springer, London, pp. 466-478. https://doi.org/10.1007/978-3-319-30671-1_34

Topic-Specific Stylistic Variations for Opinion Retrieval on Twitter. / Giachanou, Anastasia; Harvey, Morgan; Crestani, Fabio.
Advances in Information Retrieval, 38th European Conference on IR Research, ECIR 2016. ed. / N. Ferro; F. Crestani; M.-F. Meons; J. Mothe; F. Silvestri; G. M. Di Nunzio; C. Hauff; G. Silvello. London: Springer, 2016. p. 466-478.

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

TY - CHAP

T1 - Topic-Specific Stylistic Variations for Opinion Retrieval on Twitter

AU - Giachanou, Anastasia

AU - Harvey, Morgan

AU - Crestani, Fabio

PY - 2016/4

Y1 - 2016/4

N2 - Twitter has emerged as a popular platform for sharing information and expressing opinions. Twitter opinion retrieval is recognized as a powerful tool for finding people's attitudes on different topics. However, the vast amount of data and the informal language of tweets make opinion retrieval on Twitter very challenging. In this paper, we propose to leverage topic-specific stylistic variations to retrieve tweets that are both relevant and opinionated about a particular topic. Experimental results show that integrating topic specific textual meta-communications, such as emoticons and emphatic lengthening in a ranking function can significantly improve opinion retrieval performance on Twitter.

AB - Twitter has emerged as a popular platform for sharing information and expressing opinions. Twitter opinion retrieval is recognized as a powerful tool for finding people's attitudes on different topics. However, the vast amount of data and the informal language of tweets make opinion retrieval on Twitter very challenging. In this paper, we propose to leverage topic-specific stylistic variations to retrieve tweets that are both relevant and opinionated about a particular topic. Experimental results show that integrating topic specific textual meta-communications, such as emoticons and emphatic lengthening in a ranking function can significantly improve opinion retrieval performance on Twitter.

UR - http://www.springer.com/la/book/9783319306704

U2 - 10.1007/978-3-319-30671-1_34

DO - 10.1007/978-3-319-30671-1_34

M3 - Chapter

SN - 978-3-319-30670-4

SP - 466

EP - 478

BT - Advances in Information Retrieval, 38th European Conference on IR Research, ECIR 2016

A2 - Ferro, N.

A2 - Crestani, F.

A2 - Meons, M.-F.

A2 - Mothe, J.

A2 - Silvestri, F.

A2 - Di Nunzio, G. M.

A2 - Hauff, C.

A2 - Silvello, G.

PB - Springer

CY - London

ER -

Topic-Specific Stylistic Variations for Opinion Retrieval on Twitter

Abstract

Access to Document

Other files and links

Fingerprint

Cite this