Difficulties and Improvements to Graph-Based Lexical Sentiment Analysis Using LISA

Lexical sentiment analysis (LSA) underlines a family of methods combining natural language processing, machine learning, or graph navigation techniques to identify the underlying sentiments or emotions carried in textual data. In this paper, we introduce LISA, an unsupervised word-level knowledge gr...

Full description

Saved in:
Bibliographic Details
Main Author: Fares, Mireille (author)
Other Authors: Moufarrej, Angela (author), Jreij, Eliane (author), Tekli, Joe (author), Grosky, William (author)
Format: conferenceObject
Published: 2019
Subjects:
Online Access:http://hdl.handle.net/10725/16275
https://doi.org/10.1109/ICCC.2019.00008
http://libraries.lau.edu.lb/research/laur/terms-of-use/articles.php
https://ieeexplore.ieee.org/document/8816968
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513472531791872
author Fares, Mireille
author2 Moufarrej, Angela
Jreij, Eliane
Tekli, Joe
Grosky, William
author2_role author
author
author
author
author_facet Fares, Mireille
Moufarrej, Angela
Jreij, Eliane
Tekli, Joe
Grosky, William
author_role author
dc.contributor.none.fl_str_mv Bertino, Elisa
dc.creator.none.fl_str_mv Fares, Mireille
Moufarrej, Angela
Jreij, Eliane
Tekli, Joe
Grosky, William
dc.date.none.fl_str_mv 2019
2019-08-29
2024-11-05T07:51:49Z
2024-11-05T07:51:49Z
dc.identifier.none.fl_str_mv 9781728127118
http://hdl.handle.net/10725/16275
https://doi.org/10.1109/ICCC.2019.00008
Fares, M., Moufarrej, A., Jreij, E., Tekli, J., & Grosky, W. (2019, July). Difficulties and improvements to graph-based lexical sentiment analysis using LISA. In 2019 IEEE International Conference on Cognitive Computing (ICCC) (pp. 28-35). IEEE.
http://libraries.lau.edu.lb/research/laur/terms-of-use/articles.php
https://ieeexplore.ieee.org/document/8816968
dc.language.none.fl_str_mv en
dc.publisher.none.fl_str_mv IEEE
dc.rights.*.fl_str_mv info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Cognitive science -- Data processing -- Congresses
Computational intelligence -- Congresses
dc.title.none.fl_str_mv Difficulties and Improvements to Graph-Based Lexical Sentiment Analysis Using LISA
dc.type.none.fl_str_mv Conference Paper / Proceeding
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/conferenceObject
description Lexical sentiment analysis (LSA) underlines a family of methods combining natural language processing, machine learning, or graph navigation techniques to identify the underlying sentiments or emotions carried in textual data. In this paper, we introduce LISA, an unsupervised word-level knowledge graph-based LexIcal Sentiment Analysis framework. It uses different variants of shortest path graph navigation techniques to compute and propagate affective scores in a lexical-affective graph (LAG), created by connecting a typical lexical knowledgebase (KB) like WordNet, with a reliable affect KB like WordNet-Affect Hierarchy. LISA was designed in two consecutive iterations, producing two main modules: i) LISA 1.0 for affect navigation, and ii) LISA 2.0 for affect propagation and lookup. LISA 1.0 suffered from the semantic connectivity problem shared by some existing lexicon-based methods, and required polynomial execution time. This led to the development of LISA 2.0, which i) processes affective relationships separately from lexical/semantic connections (solving the semantic connectivity problem of LISA 1.0), and ii) produces a sentiment lexicon which can be searched in logarithmic time (handling LISA 1.0's efficiency problem). Experimental results on the ANEW dataset show that LISA 2.0, while completely unsupervised, is on a par with existing supervised solutions, highlighting its quality and potential.
eu_rights_str_mv openAccess
format conferenceObject
id LAURepo_92e3cfe2d9f111543169ff2f806cdbeb
identifier_str_mv 9781728127118
Fares, M., Moufarrej, A., Jreij, E., Tekli, J., & Grosky, W. (2019, July). Difficulties and improvements to graph-based lexical sentiment analysis using LISA. In 2019 IEEE International Conference on Cognitive Computing (ICCC) (pp. 28-35). IEEE.
language_invalid_str_mv en
network_acronym_str LAURepo
network_name_str Lebanese American University repository
oai_identifier_str oai:laur.lau.edu.lb:10725/16275
publishDate 2019
publisher.none.fl_str_mv IEEE
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Difficulties and Improvements to Graph-Based Lexical Sentiment Analysis Using LISAFares, MireilleMoufarrej, AngelaJreij, ElianeTekli, JoeGrosky, WilliamCognitive science -- Data processing -- CongressesComputational intelligence -- CongressesLexical sentiment analysis (LSA) underlines a family of methods combining natural language processing, machine learning, or graph navigation techniques to identify the underlying sentiments or emotions carried in textual data. In this paper, we introduce LISA, an unsupervised word-level knowledge graph-based LexIcal Sentiment Analysis framework. It uses different variants of shortest path graph navigation techniques to compute and propagate affective scores in a lexical-affective graph (LAG), created by connecting a typical lexical knowledgebase (KB) like WordNet, with a reliable affect KB like WordNet-Affect Hierarchy. LISA was designed in two consecutive iterations, producing two main modules: i) LISA 1.0 for affect navigation, and ii) LISA 2.0 for affect propagation and lookup. LISA 1.0 suffered from the semantic connectivity problem shared by some existing lexicon-based methods, and required polynomial execution time. This led to the development of LISA 2.0, which i) processes affective relationships separately from lexical/semantic connections (solving the semantic connectivity problem of LISA 1.0), and ii) produces a sentiment lexicon which can be searched in logarithmic time (handling LISA 1.0's efficiency problem). Experimental results on the ANEW dataset show that LISA 2.0, while completely unsupervised, is on a par with existing supervised solutions, highlighting its quality and potential.1 online resource (xviii, 131 pages) : illustrations (some color)Includes bibliographical references.IEEEBertino, Elisa2024-11-05T07:51:49Z2024-11-05T07:51:49Z20192019-08-29Conference Paper / Proceedinginfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject9781728127118http://hdl.handle.net/10725/16275https://doi.org/10.1109/ICCC.2019.00008Fares, M., Moufarrej, A., Jreij, E., Tekli, J., & Grosky, W. (2019, July). Difficulties and improvements to graph-based lexical sentiment analysis using LISA. In 2019 IEEE International Conference on Cognitive Computing (ICCC) (pp. 28-35). IEEE.http://libraries.lau.edu.lb/research/laur/terms-of-use/articles.phphttps://ieeexplore.ieee.org/document/8816968eninfo:eu-repo/semantics/openAccessoai:laur.lau.edu.lb:10725/162752024-11-05T07:51:49Z
spellingShingle Difficulties and Improvements to Graph-Based Lexical Sentiment Analysis Using LISA
Fares, Mireille
Cognitive science -- Data processing -- Congresses
Computational intelligence -- Congresses
status_str publishedVersion
title Difficulties and Improvements to Graph-Based Lexical Sentiment Analysis Using LISA
title_full Difficulties and Improvements to Graph-Based Lexical Sentiment Analysis Using LISA
title_fullStr Difficulties and Improvements to Graph-Based Lexical Sentiment Analysis Using LISA
title_full_unstemmed Difficulties and Improvements to Graph-Based Lexical Sentiment Analysis Using LISA
title_short Difficulties and Improvements to Graph-Based Lexical Sentiment Analysis Using LISA
title_sort Difficulties and Improvements to Graph-Based Lexical Sentiment Analysis Using LISA
topic Cognitive science -- Data processing -- Congresses
Computational intelligence -- Congresses
url http://hdl.handle.net/10725/16275
https://doi.org/10.1109/ICCC.2019.00008
http://libraries.lau.edu.lb/research/laur/terms-of-use/articles.php
https://ieeexplore.ieee.org/document/8816968