Twitter for Sentiment Analysis: When Language Resources are Not Available

Pak, Alexander; Paroubek, Patrick

doi:10.1109/dexa.2011.86

Cited by 115 publications

(124 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For more details, see http://www.androidauthority.com/google-translate-machine-learning-chinese-718813/. Prior research252627 on Chinese sentiment analysis has shown that using Google translate to translate Chinese reviews into English reviews improves the sentiment classification performance. In Pak et al 26,.…”

Section: Methodsmentioning

confidence: 99%

Temporal Topic Modeling to Assess Associations between News Trends and Infectious Disease Outbreaks

Ghosh

Chakraborty

Nsoesie

et al. 2017

Sci Rep

View full text Add to dashboard Cite

In retrospective assessments, internet news reports have been shown to capture early reports of unknown infectious disease transmission prior to official laboratory confirmation. In general, media interest and reporting peaks and wanes during the course of an outbreak. In this study, we quantify the extent to which media interest during infectious disease outbreaks is indicative of trends of reported incidence. We introduce an approach that uses supervised temporal topic models to transform large corpora of news articles into temporal topic trends. The key advantages of this approach include: applicability to a wide range of diseases and ability to capture disease dynamics, including seasonality, abrupt peaks and troughs. We evaluated the method using data from multiple infectious disease outbreaks reported in the United States of America (U.S.), China, and India. We demonstrate that temporal topic trends extracted from disease-related news reports successfully capture the dynamics of multiple outbreaks such as whooping cough in U.S. (2012), dengue outbreaks in India (2013) and China (2014). Our observations also suggest that, when news coverage is uniform, efficient modeling of temporal topic trends using time-series regression techniques can estimate disease case counts with increased precision before official reports by health organizations.

show abstract

Section: Methodsmentioning

confidence: 99%

Temporal Topic Modeling to Assess Associations between News Trends and Infectious Disease Outbreaks

Ghosh

Chakraborty

Nsoesie

et al. 2017

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In this technique the features used are unigram and n-gram [8]. In unigram features, words and symbols in the document are represented into vector shapes, and each word or symbol is counted as a single feature.…”

Section: Using Machine Learning Techniquesmentioning

confidence: 99%

“…Topics are limited regarding the comments about the Government's Work Programs in the City of Bandung in era of Mr. Ridwan Kamil. Methods of data collection used refers to the study "Twitter as a Corpus for Sentiment Analysis and Opinion Mining" [8] and "Analisis Sentimen Pada Dokumen Berbahasa Indonesia dengan Pendekatan Support Vector Machine". [6] For the process of crawling, it uses the keyword of several Special Work Program, such as: the city park, culinary night, etc.…”

Section: Data Collectionmentioning

confidence: 99%

“…Researches about sentiment analysis of tweet have been conducted by many researchers such as "Twitter as a Corpus for Sentiment Analysis and Opinion Mining" [8] which provides a method of data collection. Furthermore, the research entitled "Analisis Sentimen Pada Dokumen Berbahasa Indonesia dengan Pendekatan Support Vector Machine" [6] is added language detection process to get data in Indonesian language and to produce result that the classification process that is supervised by an algorithm using Support Vector Machine (SVM) has level of accuracy that is better than the Naïve Bayes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Framework for Sentiment Analysis Implementation of Indonesian Language Tweet on Twitter

Asniar

Aditya

2017

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Abstract. Sentiment analysis is the process of understanding, extracting, and processing the textual data automatically to obtain information. Sentiment analysis can be used to see opinion on an issue and identify a response to something. Millions of digital data are still not used to be able to provide any information that has usefulness, especially for government. Sentiment analysis in government is used to monitor the work programs of the government such as the Government of Bandung City through social media data. The analysis can be used quickly as a tool to see the public response to the work programs, so the next strategic steps can be taken. This paper adopts Support Vector Machine as a supervised algorithm for sentiment analysis. It presents a framework for sentiment analysis implementation of Indonesian language tweet on twitter for Work Programs of Government of Bandung City. The results of this paper can be a reference for decision making in local government.

show abstract

“…Pak and Paroubek [20] built a sentiment lexicon using Twitter 14 . They downloaded tweets and divided them into positive and negative tweets depending on the inclusion of positive or negative emoticons.…”

Section: Building Sentiment Dictionariesmentioning

confidence: 99%

Building sentiment lexicons based on recommending services for the Polish language

Gliwa

Zygmunt

Dąbrowski

2016

csci

View full text Add to dashboard Cite

Twitter for Sentiment Analysis: When Language Resources are Not Available

Cited by 115 publications

References 9 publications

Temporal Topic Modeling to Assess Associations between News Trends and Infectious Disease Outbreaks

Temporal Topic Modeling to Assess Associations between News Trends and Infectious Disease Outbreaks

A Framework for Sentiment Analysis Implementation of Indonesian Language Tweet on Twitter

Building sentiment lexicons based on recommending services for the Polish language

Contact Info

Product

Resources

About