TY - JOUR
T1 - Mining the Impact of Social Media on High-Frequency Financial data
AU - Hashemi, Ray R.
AU - Ardakani, Omid
AU - Young, Jeffrey
AU - Tamrakar, Chanchal
N1 - Establishing the relationship between stock price changes of a fortune 500 company and events (such as political, social, and/or business) is a multi-dimensional complex problem. However, such events change the social mood, which manifests itself in social media communications. Therefore, we collected time-series high frequency financial (HFF) data alongside corresponding time-series tweets about the same company for six months in 2019.
PY - 2022/6/22
Y1 - 2022/6/22
N2 - Establishing the relationship between stock price changes of a fortune 500 company and events (such as political, social, and/or business) is a multi-dimensional complex problem. However, such events change the social mood, which manifests itself in social media communications. Therefore, we collected time-series high frequency financial (HFF) data alongside corresponding time-series tweets about the same company for six months in 2019. Five months of data was used to (a) mine impactful tweets (nuggets) on minute-by-minute stock price changes, (b) discover and validate the nuggets profile, (c) predict future impactful tweets prior to their effects on the stock price using the HFF data and tweets for the sixth month as a test set, and (d) maintain an up-to-date nuggets profile. The results revealed successful detection of nuggets of tweets with a certainty factor close to 80%. Such prediction may greatly affect the decisions regarding market analytics.
AB - Establishing the relationship between stock price changes of a fortune 500 company and events (such as political, social, and/or business) is a multi-dimensional complex problem. However, such events change the social mood, which manifests itself in social media communications. Therefore, we collected time-series high frequency financial (HFF) data alongside corresponding time-series tweets about the same company for six months in 2019. Five months of data was used to (a) mine impactful tweets (nuggets) on minute-by-minute stock price changes, (b) discover and validate the nuggets profile, (c) predict future impactful tweets prior to their effects on the stock price using the HFF data and tweets for the sixth month as a test set, and (d) maintain an up-to-date nuggets profile. The results revealed successful detection of nuggets of tweets with a certainty factor close to 80%. Such prediction may greatly affect the decisions regarding market analytics.
UR - https://ieeexplore.ieee.org/document/9798913/
M3 - Article
JO - International Conference on Computational Science and Computational Intelligence (CSCI)
JF - International Conference on Computational Science and Computational Intelligence (CSCI)
ER -