Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/31273
Registo completo
Campo DC | Valor | Idioma |
---|---|---|
dc.contributor.author | Oliveira, Nuno | por |
dc.contributor.author | Cortez, Paulo | por |
dc.contributor.author | Areal, Nelson | por |
dc.date.accessioned | 2014-11-25T13:24:57Z | - |
dc.date.available | 2014-11-25T13:24:57Z | - |
dc.date.issued | 2014 | - |
dc.identifier.isbn | 978-1-4503-2627-8 | - |
dc.identifier.uri | https://hdl.handle.net/1822/31273 | - |
dc.description.abstract | Sentiment analysis has been increasingly applied to the stock market domain. In particular, investor sentiment indicators can be used to model and predict stock market variables. In this context, the quality of the sentiment analysis is highly dependent of the opinion lexicon adopted. However, there is a lack of lexicons adjusted to microblogging stock market data. In this work, we propose an automatic procedure for the creation of such lexicon by exploring a large set of labeled messages from StockTwits, a popular financial microblogging service, and using four statistical measures: adaptations of the known TF-IDF, Information Gain, Class Percentage, and a newly proposed Weighted Class Probability. The obtained lexicons are competitive when compared with a set of six reference lexicons. Moreover, we verified that it is beneficial to use continuous sentiment scores instead of sentiment labels. | por |
dc.description.sponsorship | We wish to thank StockTwits for kindly providing their data. This work has been supported by FCT - Fundacao para a Ciencia e Tecnologia within the Project Scope: PEst-OE/EEI/UI0319/2014. | por |
dc.language.iso | eng | por |
dc.publisher | ACM | por |
dc.rights | openAccess | por |
dc.subject | Sentiment analysis | por |
dc.subject | Opinion mining | por |
dc.subject | Stock market | por |
dc.subject | Lexicon | por |
dc.subject | Microblogging data | por |
dc.subject | Information retrieval | por |
dc.title | Automatic creation of stock market lexicons for sentiment analysis using StockTwits data | por |
dc.type | conferencePaper | por |
dc.peerreviewed | yes | por |
dc.relation.publisherversion | The original publication is available at http://dx.doi.org/10.1145/2628194.2628235 | por |
sdum.publicationstatus | published | por |
oaire.citationStartPage | 115 | por |
oaire.citationEndPage | 123 | por |
oaire.citationTitle | Proceedings of the 18th International Database Engineering & Applications Symposium (IDEAS'14) | por |
dc.identifier.doi | 10.1145/2628194.2628235 | por |
dc.subject.fos | Ciências Naturais::Ciências da Computação e da Informação | por |
dc.subject.wos | Science & Technology | por |
sdum.conferencePublication | Proceedings of the 18th International Database Engineering & Applications Symposium (IDEAS'14) | por |
sdum.bookTitle | PROCEEDINGS OF THE 18TH INTERNATIONAL DATABASE ENGINEERING AND APPLICATIONS SYMPOSIUM (IDEAS14) | por |
Aparece nas coleções: | EEG - Comunicações e Conferências |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
2014-ideas.pdf | 347,51 kB | Adobe PDF | Ver/Abrir |