Learning Text Patterns to Detect Opinion Targets

Filipa Peleja; João Magalhães

doi:10.5220/0005612603370343

Learning Text Patterns to Detect Opinion Targets

Filipa Peleja, João Magalhães

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

2 Citations (Scopus)

Abstract

Exploiting sentiment relations to capture opinion targets has recently caught the interest of many researchers. In many cases target entities are themselves part of the sentiment lexicon creating a loop from which it is difficult to infer the overall sentiment to the target entities. In the present work we propose to detect opinion targets by extracting syntactic patterns from short-texts. Experiments show that our method was able to successfully extract 1,879 opinion targets from a total of 2,052 opinion targets. Furthermore, the proposed method obtains comparable results to SemEval 2015 opinion target models in which we observed the syntactic structure relation that exists between sentiment words and their target.

Original language	English
Title of host publication	KDIR 2015 - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval, part of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2015), Volume 1, Lisbon, Portugal, November 12-14, 2015
Pages	337-343
Number of pages	7
DOIs	https://doi.org/10.5220/0005612603370343
Publication status	Published - 2015
Event	7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2015 - Lisbon, Portugal Duration: 12 Nov 2015 → 14 Nov 2015

Conference

Conference	7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2015
Country/Territory	Portugal
City	Lisbon
Period	12/11/15 → 14/11/15

Keywords

Opinion mining
Opinion targets
Sentiment analysis

Access to Document

10.5220/0005612603370343

Cite this

Peleja, F., & Magalhães, J. (2015). Learning Text Patterns to Detect Opinion Targets. In KDIR 2015 - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval, part of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2015), Volume 1, Lisbon, Portugal, November 12-14, 2015 (pp. 337-343) https://doi.org/10.5220/0005612603370343

Peleja, Filipa ; Magalhães, João. / Learning Text Patterns to Detect Opinion Targets. KDIR 2015 - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval, part of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2015), Volume 1, Lisbon, Portugal, November 12-14, 2015. 2015. pp. 337-343

@inproceedings{e75705688245478daaedc9e2186e1b8c,

title = "Learning Text Patterns to Detect Opinion Targets",

abstract = "Exploiting sentiment relations to capture opinion targets has recently caught the interest of many researchers. In many cases target entities are themselves part of the sentiment lexicon creating a loop from which it is difficult to infer the overall sentiment to the target entities. In the present work we propose to detect opinion targets by extracting syntactic patterns from short-texts. Experiments show that our method was able to successfully extract 1,879 opinion targets from a total of 2,052 opinion targets. Furthermore, the proposed method obtains comparable results to SemEval 2015 opinion target models in which we observed the syntactic structure relation that exists between sentiment words and their target.",

keywords = "Opinion mining, Opinion targets, Sentiment analysis",

author = "Filipa Peleja and Jo{\~a}o Magalh{\~a}es",

note = "Sem PDF.; 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2015 ; Conference date: 12-11-2015 Through 14-11-2015",

year = "2015",

doi = "10.5220/0005612603370343",

language = "English",

isbn = "978-989758158-8",

pages = "337--343",

booktitle = "KDIR 2015 - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval, part of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2015), Volume 1, Lisbon, Portugal, November 12-14, 2015",

}

Peleja, F & Magalhães, J 2015, Learning Text Patterns to Detect Opinion Targets. in KDIR 2015 - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval, part of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2015), Volume 1, Lisbon, Portugal, November 12-14, 2015. pp. 337-343, 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2015, Lisbon, Portugal, 12/11/15. https://doi.org/10.5220/0005612603370343

Learning Text Patterns to Detect Opinion Targets. / Peleja, Filipa; Magalhães, João.
KDIR 2015 - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval, part of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2015), Volume 1, Lisbon, Portugal, November 12-14, 2015. 2015. p. 337-343.

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

TY - GEN

T1 - Learning Text Patterns to Detect Opinion Targets

AU - Peleja, Filipa

AU - Magalhães, João

N1 - Sem PDF.

PY - 2015

Y1 - 2015

N2 - Exploiting sentiment relations to capture opinion targets has recently caught the interest of many researchers. In many cases target entities are themselves part of the sentiment lexicon creating a loop from which it is difficult to infer the overall sentiment to the target entities. In the present work we propose to detect opinion targets by extracting syntactic patterns from short-texts. Experiments show that our method was able to successfully extract 1,879 opinion targets from a total of 2,052 opinion targets. Furthermore, the proposed method obtains comparable results to SemEval 2015 opinion target models in which we observed the syntactic structure relation that exists between sentiment words and their target.

AB - Exploiting sentiment relations to capture opinion targets has recently caught the interest of many researchers. In many cases target entities are themselves part of the sentiment lexicon creating a loop from which it is difficult to infer the overall sentiment to the target entities. In the present work we propose to detect opinion targets by extracting syntactic patterns from short-texts. Experiments show that our method was able to successfully extract 1,879 opinion targets from a total of 2,052 opinion targets. Furthermore, the proposed method obtains comparable results to SemEval 2015 opinion target models in which we observed the syntactic structure relation that exists between sentiment words and their target.

KW - Opinion mining

KW - Opinion targets

KW - Sentiment analysis

U2 - 10.5220/0005612603370343

DO - 10.5220/0005612603370343

M3 - Conference contribution

SN - 978-989758158-8

SP - 337

EP - 343

BT - KDIR 2015 - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval, part of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2015), Volume 1, Lisbon, Portugal, November 12-14, 2015

T2 - 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2015

Y2 - 12 November 2015 through 14 November 2015

ER -

Peleja F, Magalhães J. Learning Text Patterns to Detect Opinion Targets. In KDIR 2015 - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval, part of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2015), Volume 1, Lisbon, Portugal, November 12-14, 2015. 2015. p. 337-343 doi: 10.5220/0005612603370343

Learning Text Patterns to Detect Opinion Targets

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this