A Large Scale Study to Understand the Relation between Twitter and Financial Market

Cazzoli, Lorenzo; Sharma, Rajesh; Treccani, Michele; Lillo, Fabrizio

doi:10.1109/enic.2016.022

Cited by 18 publications

(17 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, subsequent work [65] evaluated the informativeness of sentiment-and volume-derived predictors, showing that the sentiment of tweets contains signi cantly more information for predicting stock prices than just their volume. e role of in uencers in social media has also been identi ed as a strong contributing factor to the formation of market trends [13]. Others have instead used weblogs for studying the relationships between di erent companies [39].…”

Section: Finance and Social Mediamentioning

confidence: 99%

Cashtag piggybacking: uncovering spam and bot activity in stock microblogs on Twitter

Cresci,

Lillo,

Regoli

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

Microblogs are increasingly exploited for predicting prices and traded volumes of stocks in nancial markets. However, it has been demonstrated that much of the content shared in microblogging platforms is created and publicized by bots and spammers. Yet, the presence (or lack thereof) and the impact of fake stock microblogs has never systematically been investigated before. Here, we study 9M tweets related to stocks of the 5 main nancial markets in the US. By comparing tweets with nancial data from Google Finance, we highlight important characteristics of Twi er stock microblogs. More importantly, we uncover a malicious practicereferred to as cashtag piggybacking -perpetrated by coordinated groups of bots and likely aimed at promoting low-value stocks by exploiting the popularity of high-value ones. Among the ndings of our study is that as much as 71% of the authors of suspicious nancial tweets are classi ed as bots by a state-of-the-art spambot detection algorithm. Furthermore, 37% of them were suspended by Twi er a few months a er our investigation. Our results call for the adoption of spam and bot detection techniques in all studies and applications that exploit user-generated content for predicting the stock market.

show abstract

Section: Finance and Social Mediamentioning

confidence: 99%

Cashtag piggybacking: uncovering spam and bot activity in stock microblogs on Twitter

Cresci,

Lillo,

Regoli

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Boasting over 313 million active users worldwide, Twitter provides for fast dissemination of information [45][46] [47]. Twitter has been the subject of several experiments by researchers for its use in discussing financial stocks [48][49] [50].…”

Section: B Social Mediamentioning

confidence: 99%

Big Data Fusion Model for Heterogeneous Financial Market Data (FinDf)

Evans

Owda

Crockett

et al. 2018

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

The dawn of big data has seen the volume, variety, and velocity of data sources increase dramatically. Enormous amounts of structured, semi-structured and unstructured heterogeneous data can be garnered at a rapid rate, making analysis of such big data a herculean task. This has never been truer for data relating to financial stock markets, the biggest challenge being the 7 Vs of big data which relate to the collection, pre-processing, storage and real-time processing of such huge quantities of disparate data sources. Data fusion techniques have been adopted in a wide number of fields to cope with such vast amounts of heterogeneous data from multiple sources and fuse them together in order to produce a more comprehensive view of the data and its underlying relationships. Research into the fusing of heterogeneous financial data is scant within the literature, with existing work only taking into consideration the fusing of text-based financial documents. The lack of integration between financial stock market data, social media comments, financial discussion board posts and broker agencies means that the benefits of data fusion are not being realised to their full potential. This paper proposes a novel data fusion model, inspired by the data fusion model introduced by the Joint Directors of Laboratories, for the fusing of disparate data sources relating to financial stocks. Data with a diverse set of features from different data sources will supplement each other in order to obtain a Smart Data Layer, which will assist in scenarios such as irregularity detection and prediction of stock prices.

show abstract

“…Understanding the information diffusion processes on these networks may help addressing many real world challenges such as investigation and prevention of terrorism activity [4]. The data on social media can also be analysed with an objective of observing the trends of elections results [1], correlating events between social media platforms such as Twitter and stock market [2].…”

Section: Introductionmentioning

confidence: 99%

Complex Networks and Their Applications VII

2019

Studies in Computational Intelligence

View full text Add to dashboard Cite

Online social media has become a part of everyday life of modern society. A lot of information is created on these platforms and shared with the community continuously. Predicting information diffusion on online social platforms has been studied in the past by many researchers as it has its applications in various domains such as viral marketing, news propagation etc. Some information spreads faster compared to others depending on topic of interest of the online users. In this work, we investigate the information diffusion problem with Twitter data as a use case study. We define tweet popularity as number of retweets any original message receives. In total we extracted 27 features which can be categorised into content, user, sentiment and initial retweeting behaviour for creating our prediction model. We study the problem of predicting as a multiclass prediction task. Three datasets from Twitter about three different topics are collected and analysed for building and testing various models based on different machine learning algorithms. The models were able to predict up to 60% of overall accuracy and an F1 score of 67% is obtained. The models were created using one of the dataset and tested on all the datasets, which shows that the model is robust enough to handle information diffusions associated with different topics.

show abstract

A Large Scale Study to Understand the Relation between Twitter and Financial Market

Cited by 18 publications

References 15 publications

Cashtag piggybacking: uncovering spam and bot activity in stock microblogs on Twitter

Cashtag piggybacking: uncovering spam and bot activity in stock microblogs on Twitter

Big Data Fusion Model for Heterogeneous Financial Market Data (FinDf)

Complex Networks and Their Applications VII

Contact Info

Product

Resources

About