Lexical approaches for sentiment analysis like SentiWordNet rely upon a fixed dictionary of words with fixed sentiment, i.e., sentiment that does not change. With the rise of Web 2.0 however, what we observe more and more often is that words that are not sentimental per se, are often associated with positive/negative feelings, for example, "refugees", "Trump", "iphone". Typically, those feelings are temporary as responses to external events; for example, "iphone" sentiment upon latest iphone version release or "Trump" sentiment after USA withdraw from Paris climate agreement. In this work, we propose an approach for extracting and monitoring what we call ephemeral words from social streams; these are words that convey sentiment without being sentimental and their sentiment might change with time. Such sort of words cannot be part of a lexicon like SentiWordNet since their sentiment has an ephemeral character, however detecting such words and estimating their sentiment can significantly improve the performance of lexicon-based approaches, as our experiments show.
Beschreibung
Enriching Lexicons with Ephemeral Words for Sentiment Analysis in Social Streams
%0 Conference Paper
%1 Melidis:2018:ELE:3227609.3227664
%A Melidis, Damianos P.
%A Campero, Alvaro Veizaga
%A Iosifidis, Vasileios
%A Ntoutsi, Eirini
%A Spiliopoulou, Myra
%B Proceedings of the 8th International Conference on Web Intelligence, Mining and Semantics
%C New York, NY, USA
%D 2018
%E Akerkar, Rajendra
%E Ivanovic, Mirjana
%E Kim, Sang-Wook
%E Manolopoulos, Yannis
%E Rosati, Riccardo
%E Savic, Milos
%E Badica, Costin
%E Radovanovic, Milos
%I ACM
%K alexandriaproj lexicon myown oscarproj sentiment-analysis
%P 38:1--38:8
%R 10.1145/3227609.3227664
%T Enriching Lexicons with Ephemeral Words for Sentiment Analysis in Social Streams
%U http://doi.acm.org/10.1145/3227609.3227664
%X Lexical approaches for sentiment analysis like SentiWordNet rely upon a fixed dictionary of words with fixed sentiment, i.e., sentiment that does not change. With the rise of Web 2.0 however, what we observe more and more often is that words that are not sentimental per se, are often associated with positive/negative feelings, for example, "refugees", "Trump", "iphone". Typically, those feelings are temporary as responses to external events; for example, "iphone" sentiment upon latest iphone version release or "Trump" sentiment after USA withdraw from Paris climate agreement. In this work, we propose an approach for extracting and monitoring what we call ephemeral words from social streams; these are words that convey sentiment without being sentimental and their sentiment might change with time. Such sort of words cannot be part of a lexicon like SentiWordNet since their sentiment has an ephemeral character, however detecting such words and estimating their sentiment can significantly improve the performance of lexicon-based approaches, as our experiments show.
%@ 978-1-4503-5489-9
@inproceedings{Melidis:2018:ELE:3227609.3227664,
abstract = {Lexical approaches for sentiment analysis like SentiWordNet rely upon a fixed dictionary of words with fixed sentiment, i.e., sentiment that does not change. With the rise of Web 2.0 however, what we observe more and more often is that words that are not sentimental per se, are often associated with positive/negative feelings, for example, "refugees", "Trump", "iphone". Typically, those feelings are temporary as responses to external events; for example, "iphone" sentiment upon latest iphone version release or "Trump" sentiment after USA withdraw from Paris climate agreement. In this work, we propose an approach for extracting and monitoring what we call ephemeral words from social streams; these are words that convey sentiment without being sentimental and their sentiment might change with time. Such sort of words cannot be part of a lexicon like SentiWordNet since their sentiment has an ephemeral character, however detecting such words and estimating their sentiment can significantly improve the performance of lexicon-based approaches, as our experiments show.},
acmid = {3227664},
added-at = {2018-10-11T10:33:21.000+0200},
address = {New York, NY, USA},
articleno = {38},
author = {Melidis, Damianos P. and Campero, Alvaro Veizaga and Iosifidis, Vasileios and Ntoutsi, Eirini and Spiliopoulou, Myra},
biburl = {https://www.bibsonomy.org/bibtex/26a05dbdc2a947bda540dad48d9c4a326/damianosmel},
booktitle = {Proceedings of the 8th International Conference on Web Intelligence, Mining and Semantics},
description = {Enriching Lexicons with Ephemeral Words for Sentiment Analysis in Social Streams},
doi = {10.1145/3227609.3227664},
editor = {Akerkar, Rajendra and Ivanovic, Mirjana and Kim, Sang-Wook and Manolopoulos, Yannis and Rosati, Riccardo and Savic, Milos and Badica, Costin and Radovanovic, Milos},
interhash = {d671a7a81f3801547648d8b90f8dc8a9},
intrahash = {6a05dbdc2a947bda540dad48d9c4a326},
isbn = {978-1-4503-5489-9},
keywords = {alexandriaproj lexicon myown oscarproj sentiment-analysis},
location = {Novi Sad, Serbia},
numpages = {8},
pages = {38:1--38:8},
publisher = {ACM},
series = {WIMS '18},
timestamp = {2019-01-22T11:36:58.000+0100},
title = {Enriching Lexicons with Ephemeral Words for Sentiment Analysis in Social Streams},
url = {http://doi.acm.org/10.1145/3227609.3227664},
year = 2018
}