In this paper, we describe how we created two state-of-the-art SVM classifiers, one to detect the sentiment of messages such as tweets and SMS (message-level task) and one to detect the sentiment of a term within a message (term-level task). Among submissions from 44 teams in a competition, our submissions stood first in both tasks on tweets, obtaining an F-score of 69.02 in the message-level task and 88.93 in the term-level task. We implemented a variety of surface-form, semantic, and sentiment features. We also generated two large word‐sentiment association lexicons, one from tweets with sentiment-word hashtags, and one from tweets with emoticons. In the message-level task, the lexicon-based features provided a gain of 5 F-score points over all others. Both of our systems can be replicated using freely available resources. 1
Description
A study by NRC-Canada that aimed to build a state-of-the-art model for sentiment analysis on tweets.
%0 Generic
%1 Saif2013
%A Mohammad, Saif M.
%A Kiritchenko, Svetlana
%A Zhu, Xiao-Dan
%D 2013
%J ArXiv
%K sentiment_analysis twitter related_works_benchmark posted_with_chatgpt
%T NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets
%U https://www.semanticscholar.org/paper/506b0cad3d660a53364d622e49673ae5f95526c8
%V abs/1308.6242
%X In this paper, we describe how we created two state-of-the-art SVM classifiers, one to detect the sentiment of messages such as tweets and SMS (message-level task) and one to detect the sentiment of a term within a message (term-level task). Among submissions from 44 teams in a competition, our submissions stood first in both tasks on tweets, obtaining an F-score of 69.02 in the message-level task and 88.93 in the term-level task. We implemented a variety of surface-form, semantic, and sentiment features. We also generated two large word‐sentiment association lexicons, one from tweets with sentiment-word hashtags, and one from tweets with emoticons. In the message-level task, the lexicon-based features provided a gain of 5 F-score points over all others. Both of our systems can be replicated using freely available resources. 1
@JournalArticle{Saif2013,
abstract = {In this paper, we describe how we created two state-of-the-art SVM classifiers, one to detect the sentiment of messages such as tweets and SMS (message-level task) and one to detect the sentiment of a term within a message (term-level task). Among submissions from 44 teams in a competition, our submissions stood first in both tasks on tweets, obtaining an F-score of 69.02 in the message-level task and 88.93 in the term-level task. We implemented a variety of surface-form, semantic, and sentiment features. We also generated two large word‐sentiment association lexicons, one from tweets with sentiment-word hashtags, and one from tweets with emoticons. In the message-level task, the lexicon-based features provided a gain of 5 F-score points over all others. Both of our systems can be replicated using freely available resources. 1},
added-at = {2023-09-22T12:33:09.000+0200},
author = {Mohammad, Saif M. and Kiritchenko, Svetlana and Zhu, Xiao-Dan},
biburl = {https://www.bibsonomy.org/bibtex/225ddd8685269a80a690ceba8d885c434/tomvoelker},
day = 28,
description = {A study by NRC-Canada that aimed to build a state-of-the-art model for sentiment analysis on tweets.},
interhash = {659eb7a5f0bddf3ed7aabbb5677214ec},
intrahash = {25ddd8685269a80a690ceba8d885c434},
journal = {ArXiv},
keywords = {sentiment_analysis twitter related_works_benchmark posted_with_chatgpt},
month = {8},
timestamp = {2023-09-22T12:33:09.000+0200},
title = {NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets},
url = {https://www.semanticscholar.org/paper/506b0cad3d660a53364d622e49673ae5f95526c8},
volume = {abs/1308.6242},
year = 2013
}