DATA MINING TWITTER TO PREDICT STOCK MARKET MOVEMENTS
In this paper we apply sentiment analysis of Twitter data from July through December, 2013 to find correlation between users’ sentiments and NASDAQ closing price and trading volume. Our analysis is based on the Affective Norms for English Words (ANEW). We propose a novel way of determining weighted...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
National Institute for Economic Research
2015-04-01
|
| Series: | Economy and Sociology |
| Subjects: | |
| Online Access: | ftp://ince.md/Economie%20si%20Sociologie%20nr_1-2015/16.Pecionchin.pdf |
| _version_ | 1818345162275815424 |
|---|---|
| author | Maxim PECIONCHIN Muhammad USMAN |
| author_facet | Maxim PECIONCHIN Muhammad USMAN |
| author_sort | Maxim PECIONCHIN |
| collection | DOAJ |
| description | In this paper we apply sentiment analysis of Twitter data from July through December, 2013 to find correlation between users’ sentiments and NASDAQ closing price and trading volume. Our analysis is based on the Affective Norms for English Words (ANEW). We propose a novel way of determining weighted mood level based on PageRank algorithm. We find that sentiment data is Granger-causal to financial market performance with high degree of significance. “Happy” and “sad” sentiment variables’ lags are strongly correlated with closing price and “excited” and “calm” lags are strongly correlated with trading volume. |
| first_indexed | 2024-12-13T16:57:59Z |
| format | Article |
| id | doaj.art-9b96accf4c704685ab634ade80b10978 |
| institution | Directory Open Access Journal |
| issn | 1857-4130 1857-4130 |
| language | English |
| last_indexed | 2024-12-13T16:57:59Z |
| publishDate | 2015-04-01 |
| publisher | National Institute for Economic Research |
| record_format | Article |
| series | Economy and Sociology |
| spelling | doaj.art-9b96accf4c704685ab634ade80b109782022-12-21T23:37:52ZengNational Institute for Economic ResearchEconomy and Sociology1857-41301857-41302015-04-011105112DATA MINING TWITTER TO PREDICT STOCK MARKET MOVEMENTSMaxim PECIONCHIN0Muhammad USMAN1PhD candidate University of International Business and Economics, Beijing, ChinaPhD candidate University of International Business and Economics, Beijing, ChinaIn this paper we apply sentiment analysis of Twitter data from July through December, 2013 to find correlation between users’ sentiments and NASDAQ closing price and trading volume. Our analysis is based on the Affective Norms for English Words (ANEW). We propose a novel way of determining weighted mood level based on PageRank algorithm. We find that sentiment data is Granger-causal to financial market performance with high degree of significance. “Happy” and “sad” sentiment variables’ lags are strongly correlated with closing price and “excited” and “calm” lags are strongly correlated with trading volume.ftp://ince.md/Economie%20si%20Sociologie%20nr_1-2015/16.Pecionchin.pdfsentiment analysisopinion miningfinancial markettrading volume. |
| spellingShingle | Maxim PECIONCHIN Muhammad USMAN DATA MINING TWITTER TO PREDICT STOCK MARKET MOVEMENTS Economy and Sociology sentiment analysis opinion mining financial market trading volume. |
| title | DATA MINING TWITTER TO PREDICT STOCK MARKET MOVEMENTS |
| title_full | DATA MINING TWITTER TO PREDICT STOCK MARKET MOVEMENTS |
| title_fullStr | DATA MINING TWITTER TO PREDICT STOCK MARKET MOVEMENTS |
| title_full_unstemmed | DATA MINING TWITTER TO PREDICT STOCK MARKET MOVEMENTS |
| title_short | DATA MINING TWITTER TO PREDICT STOCK MARKET MOVEMENTS |
| title_sort | data mining twitter to predict stock market movements |
| topic | sentiment analysis opinion mining financial market trading volume. |
| url | ftp://ince.md/Economie%20si%20Sociologie%20nr_1-2015/16.Pecionchin.pdf |
| work_keys_str_mv | AT maximpecionchin dataminingtwittertopredictstockmarketmovements AT muhammadusman dataminingtwittertopredictstockmarketmovements |