Sentiment Analysis of Twitter Data within Big Data Distributed Environment for Stock Prediction

Skuza, Michał; Romanowski, Andrzej

doi:10.15439/2015f230

Cited by 54 publications

(33 citation statements)

References 12 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Current stock market classification models are still suffering from low classification accuracy [14], [15]. Hence, this weakness in the models has a direct effect on the reliability of stock market indicators such as "series of statistical figures" and "financial reports" that explains the stock behavior [16], [17].…”

Section: Statement Of Problemmentioning

confidence: 99%

Sentiment Classification f rom Social Media f or Stock Prediction w ith Data Mining

Triany*,

Isa

2020

IJITEE

View full text Add to dashboard Cite

Social media currently plays an important role as a means of exchanging information. Through social media, information is obtained that can be used to see people's sentiments about a product or an event. Social media is a viable option to attract public sentiment through a method called sentiment analysis. The thing done is attracting sentiment from internet users through the posts made. In this way, sentiment data can be collected quickly and easily. Current economic behavior has proven that financial decisions are driven significantly by sentiment. The level of collective optimism or pessimism in society can influence investor decisions. Sentiment can also be interpreted as something that is felt by someone, both positive and negative. Sentiments and perceptions are psychological constructs and therefore difficult to measure in the analysis. This study focuses on sentiment analysis of information obtained from Twitter about stocks. For sentiment classification process ensemble methods of Naïve Bayes and SVM is used. Sentiment results are classified as positive or negative. We are expecting to see if there is connection between sentiment analysis from social media in predicting movement of IHSG stock price. As a result, we obtained strong correlation with coefficient of correlation r= 0.56609.

show abstract

Section: Statement Of Problemmentioning

confidence: 99%

Sentiment Classification f rom Social Media f or Stock Prediction w ith Data Mining

Triany*,

Isa

2020

IJITEE

View full text Add to dashboard Cite

show abstract

“…The following section addressing the studies analyzing a huge quantity of data generated by social media events, news data and other data sources with the use of big data analytics. The authors in [11] implemented a Naive Bayes algorithm for forecasting stock prices of data gathered from social media events in distributed Map-Reduce programming model. Two input datasets for varied time intervals (5 minutes, 90 minutes, 15 minutes) were used for the prediction task.…”

Section: B Big Data Framework and Machine Learning Techniquesmentioning

confidence: 99%

Short Term Stock Movements with Big Data and Market Sentiments Analytics

Kalra¹,

Gupta²,

Prasad³

2019

IJITEE

View full text Add to dashboard Cite

Machine Learning Techniques and Big Data analytics are two central points of data science. Big Data is important for organizations to gain insights into it and machine learning techniques are one of the substantial assets for analyzing a massive amount of data. In this paper, a framework has been proposed to improve the short term stock trend prediction accuracy using Logistic Regression model by means of qualitative and quantitative data. This paper makes a comprehensive survey of stock market trend prediction with the accumulation of various data sources by applying machine learning techniques and by using big data analytics approach. The model has been implemented in Big data Framework with Hadoop and Apache Spark. For qualitative data Tweets sentiments and news sentiments has been taken in to account and for quantitative data Google trends and historical data are considered. The proposed system has enhanced the prediction accuracy about 3-4 % in comparison to existing models by supplying Google trend as input data in addition to market sentiments and historical data. The implemented model can help the investors to take short term decisions to make money in the security market and the survey would help in finding the most effective resources which overly influence the stock prices.

show abstract

“…Many new models have been developed nowadays, but each model has its advantages and disadvantages. Current stock market classification models are still suffering from low classification accuracy (L. Zhang, 2013;Meesad & Li, 2014;Skuza & Romanowski, 2015;Navale, Dudhwala, Jadhav, Gabda, & Vihangam, 2016;Arvanitis & Bassiliades, 2017). Hence, this weakness in the models has a direct effect on the reliability of stock market indicators such as "series of statistical figures" and "financial reports" that explains the stock behaviour ( Bollen, Mao, & Pepe, 2011;J.…”

Section: Introductionmentioning

confidence: 99%

Stock Market Classification Model Using Sentiment Analysis on Twitter Based on Hybrid Naive Bayes Classifiers

Alkubaisi¹,

Kamaruddin²,

Husni³

2018

CIS

View full text Add to dashboard Cite

Sentiment analysis has become one of the most popular process to predict stock market behaviour based on consumer reactions. Concurrently, the availability of data from Twitter has also attracted researchers towards this research area. Most of the models related to sentiment analysis are still suffering from inaccuracies. The low accuracy in classification has a direct effect on the reliability of stock market indicators. The study primarily focuses on the analysis of the Twitter dataset. Moreover, an improved model is proposed in this study; it is designed to enhance the classification accuracy. The first phase of this model is data collection, and the second involves the filtration and transformation, which are conducted to get only relevant data. The most crucial phase is labelling, in which polarity of data is determined and negative, positive or neutral values are assigned to people opinion. The fourth phase is the classification phase in which suitable patterns of the stock market are identified by hybridizing Naïve Bayes Classifiers (NBCs), and the final phase is the performance and evaluation. This study proposes Hybrid Naïve Bayes Classifiers (HNBCs) as a machine learning method for stock market classification. The outcome is instrumental for investors, companies, and researchers whereby it will enable them to formulate their plans according to the sentiments of people. The proposed method has produced a significant result; it has achieved accuracy equals 90.38%.

show abstract

Sentiment Analysis of Twitter Data within Big Data Distributed Environment for Stock Prediction

Cited by 54 publications

References 12 publications

Sentiment Classification f rom Social Media f or Stock Prediction w ith Data Mining

Sentiment Classification f rom Social Media f or Stock Prediction w ith Data Mining

Short Term Stock Movements with Big Data and Market Sentiments Analytics

Stock Market Classification Model Using Sentiment Analysis on Twitter Based on Hybrid Naive Bayes Classifiers

Contact Info

Product

Resources

About