Agora: Introducing the Internet's Opinion to Traditional Stock Analysis and Prediction

Jayanth Rao, Venkat Ramaraju, James Smith, Ajay Bansal

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This project aims to incorporate the aspect of sentiment analysis into traditional stock analysis to enhance rating predictions by applying a reliance on the opinion of various stocks from the Internet. Headlines from seven major news publications and conversations from Yahoo Finance's 'Conversations' feature were parsed through the Valence Aware Dictionary for Sentiment Reasoning (VADER) natural language processing package to determine numerical polarities which represented positivity or negativity for a given stock ticker. These generated polarities were paired with stock metrics typically observed by stock analysts as the feature set for a Logistic Regression machine learning model. The model was trained on roughly 1500 major stocks to determine a binary classification between a 'Buy' or 'Not Buy' rating and the results of the model were inserted into the back end of the Agora Web UI which emulates search engine behavior specifically for stocks found in NYSE and NASDAQ. The model reported an accuracy of 82.5% and for most major stocks, the model's prediction correlated with stock analysts' ratings. Given the volatility of the stock market and the propensity for hive-mind behavior in online forums, the performance of the Logistic Regression model would benefit from incorporating historical stock data and more sources of opinion to balance subjectivity in the model.

Original languageEnglish (US)
Title of host publicationProceedings - 16th IEEE International Conference on Semantic Computing, ICSC 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages147-150
Number of pages4
ISBN (Electronic)9781665434188
DOIs
StatePublished - 2022
Event16th IEEE International Conference on Semantic Computing, ICSC 2022 - Virtual, Online, United States
Duration: Jan 26 2022Jan 28 2022

Publication series

NameProceedings - 16th IEEE International Conference on Semantic Computing, ICSC 2022

Conference

Conference16th IEEE International Conference on Semantic Computing, ICSC 2022
Country/TerritoryUnited States
CityVirtual, Online
Period1/26/221/28/22

Keywords

  • Logistic Regression
  • Sentiment Analysis
  • Stock Market
  • VADER

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems and Management

Fingerprint

Dive into the research topics of 'Agora: Introducing the Internet's Opinion to Traditional Stock Analysis and Prediction'. Together they form a unique fingerprint.

Cite this