Stock Price Forecasting via Sentiment Analysis on Twitter

Kordonis, John; Symeonidis, Symeon; Arampatzis, Avi

doi:10.1145/3003733.3003787

Cited by 49 publications

(31 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As a conclusion, in the same line with (Sprenger, 2010), Eliaçık and Erdoğan (2015), Kordonis et al (2016) and Kürkçü (2017), in this study, there is a significant relationship between sentiment analysis of Twitter and stock returns in both DJI and BIST indexes. It means that if the probability of positive Tweets increase, investors may expect a positive increase in the stock exchange index.…”

Section: Resultssupporting

confidence: 80%

“…In conclusion, they provided significant and strong correlation of 71,82 percentage between the sentiment mining and the fluctuations of the stock price. (Kordonis et al, 2016:1-6) collected Twitter data and they applied Naive Bayes Bernoulli and Support Vector Machine to analyze the sentiment of Twitter. As a result, they found a correlation between sentiment analysis of Twitter and stock price.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Twitter Mesajlarının Borsalar Üzerindeki Olası Etkisi

Özparlak¹

2020

Ankara Üniversitesi SBF Dergisi

View full text Add to dashboard Cite

The purpose of this research is to contribute to the academic field by demonstrating the relationship between stock related Twitter messages, their frequencies, sentiment analysis; stock return, volume, and volatility of Dow Jones Index and BIST30 & BIST100 Index. In this study, The Multinomial Naive Bayes Text Classifier is used as methodology since it is the most conventional method for text classification based on previous research. Using computational linguistics methods, 138.070 English and 34.632 Turkish tweets have been analyzed on a daily basis for a period of 8 months. The results demonstrated a strong relationship between tweets and their impact on the market. Moreover, according to results, there is a positive correlation between the number of retweets and BIST Volume lag-1 and lag+1. In addition, this article confirms that stock microblogs contain valuable information for investors and it can be an assistance in predicting the future market index.

show abstract

Section: Resultssupporting

confidence: 80%

Section: Literature Reviewmentioning

confidence: 99%

Twitter Mesajlarının Borsalar Üzerindeki Olası Etkisi

Özparlak¹

2020

Ankara Üniversitesi SBF Dergisi

View full text Add to dashboard Cite

show abstract

“…Over time, several types of analysis have been applied such as topic modeling, network analysis and opinion mining to different social media (see Table I). [11] Twitter Li et al 2016 [12] Twitter, Facebook Ahn and Spangler 2014 [13] Twitter, Facebook, Blogs Kaur et al 2019 [14] Facebook Several techniques and tools have been used for opinion mining in social media such as:…”

Section: A Opinion Mining In Social Mediamentioning

confidence: 99%

A Crowdsourcing Based Framework for Sentiment Analysis

Ennaji

Fazziki

Abdallaoui

et al. 2020

J. commun. softw. syst. (Online)

View full text Add to dashboard Cite

As social networking has spread, people started sharing their personal opinions and thoughts widely via these online platforms. The resulting vast valuable data represent a rich source for companies to deduct their products’ reputation from both social media and crowds’ judgments. To exploit this wealth of data, a framework was proposed to collect opinions and rating scores respectively from social media and crowdsourcing platform to perform sentiment analysis, provide insights about a product and give consumers’ tendencies. During the analysis process, a consumer category (strict) is excluded from the process of reaching a majority consensus. To overcome this, a fuzzy clustering is used to compute consumers’ credibility. The key novelty of our approach is the new layer of validity check using a crowdsourcing component that ensures that the results obtained from social media are supported by opinions extracted directly from real-life consumers. Finally, experiments are carried out to validate this model (Twitter and Facebook were used as data sources). The obtained results show that this approach is more efficient and accurate than existing solutions thanks to our two-layer validity check design.

show abstract

“…It is clear that the sentiment analysis is a discipline that is generating interest in the scientific community, resources have been produced such as Word2vec (Dongwen Zhang et al, 2015), WordNet Affect, SentiWord Net, among others (R. Linares et al, 2015), which allows the generation of new research cases and then a predictive analysis to examine in this case the tweets and be able to analyze the origin location, if it is classified in a positive or negative way, among others established parameters (Eric Baucom et al, 2013). Thus, observing case studies is revealed that this sentiment analysis allows us to make a prediction on a specific topic as the case of the stock market analysis, where values can be predicted according to consumer trends (John Kordonis et al, 2016). This allows us to affirm that this analysis is scalable to diverse scenarios like the tourism sector.…”

Section: Sentiment Analysismentioning

confidence: 99%

Predictive Model based on Sentiment Analysis for Peruvian SMEs in the Sustainable Tourist Sector

Zapata

Murga

Raymundo

et al. 2017

Proceedings of the 9th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management

View full text Add to dashboard Cite

In the sustainable tourist sector today, there is a wide margin of loss in small and medium-sized enterprise (SMEs) because of a poor control in logistical expenses. In other words, acquired goods are note being sold, a scenario which is very common in tourism SMEs. These SMEs buy a number of travel packages to big companies and because of the lack of demand of said packages, they expire and they become an expense, not the investment it was meant to be. To solve this problem, we propose a Predictive model based on sentiment analysis of a social networks that will help the sales decision making. Once the data of the social network is analyzed, we also propose a prediction model of tourist destinations, using this information as data source it will be able to predict the tourist interest. In addition, a case study was applied to a real Peruvian tourist enterprise showing their data before and after using the proposed model in order to validate the feasibility of proposed model.

show abstract

Stock Price Forecasting via Sentiment Analysis on Twitter

Cited by 49 publications

References 4 publications

Twitter Mesajlarının Borsalar Üzerindeki Olası Etkisi

Twitter Mesajlarının Borsalar Üzerindeki Olası Etkisi

A Crowdsourcing Based Framework for Sentiment Analysis

Predictive Model based on Sentiment Analysis for Peruvian SMEs in the Sustainable Tourist Sector

Contact Info

Product

Resources

About