• Corpus ID: 43501208

Financial Sentiment Analysis Using Machine Learning Techniques

  title={Financial Sentiment Analysis Using Machine Learning Techniques},
  author={Sarkis Agaian and Petter N. Kolm},
The rise of web content has presented a great opportunity to extract indicators of investor moods directly from news and social media. Gauging this sentiment or general prevailing attitude of investors may simplify the analysis of large, unstructured textual datasets and help anticipate price developments in the market. There are several challenges in developing a scalable and effective framework for financial sentiment analysis, including: identifying useful information content, representing… 

Figures and Tables from this paper

Evaluation of Sentiment Analysis in Finance: From Lexicons to Transformers
An evaluation platform is designed which is used to assess the effectiveness and performance of various sentiment analysis approaches, based on combinations of text representation methods and machine-learning classifiers, and shows improved efficiency of contextual embeddings in sentiment analysis.
AP Research Samples and Commentary from the 2019 Exam Administration: Sample A
  • Biology
  • 2019
Two significant issues at the forefront of its use will be addressed; the dangers/harms it will bring to health safety of humans and its negative effect on modern socioeconomic trends.
Support Vector Machine for Sentiment Analysis of Nigerian Banks Financial Tweets
Applying the model in predicting the sentiments of the five Nigerian banks twitter data reveals that the number of positive tweets within this period was slightly greater than thenumber of negative tweets, with few outliers above this range.


Fusion with sentiment scores for market research
  • S. Das, Arup Das
  • Computer Science
    2016 19th International Conference on Information Fusion (FUSION)
  • 2016
Two approaches to score sentiments from a large unstructured text corpus to fuse with other relevant structured relational data are described: a simple but effective and fast lexicon-based approach and a supervised machine learning approach where the score is derived by making use of a kernel-based classification model created from the training documents.
Deep learning for financial sentiment analysis on finance news providers
  • Min-Yuh Day, Chia-Chou Lee
  • Business
    2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)
  • 2016
The experimental result shows various financial resources have significantly different effects to investors and their investments, while the accuracy of news categorization could be improved through deep learning.
Sentiment Analysis in Financial News
The methods from machine learning outperform the methods proposed by the finance community when predicting future stock returns and suggest strategies that generate positive returns when trading with public information, but these returns vanish after accounting for trading costs.
Machine Learning Approach for Sentiment Analysis
The bag-of-words representation is commonly used for sentiment analysis, resulting into high dimensionality of the feature space, with the help of feature selection techniques which selects only important features by eliminating the noisy and irrelevant features.
Unsupervised sentiment analysis with emotional signals
This work investigates whether the signals in social media can potentially help sentiment analysis by providing a unified way to model two main categories of emotional signals, i.e., emotion indication and emotion correlation and incorporates the signals into an unsupervised learning framework for sentiment analysis.
Financial Risk Forecast Using Machine Learning and Sentiment Analysis
There is a widespread need for effective forecasting of financial risk using readily available financial measures, but the complicated environment facing financial practitioners and business
Opinion Mining and Sentiment Analysis
This survey covers techniques and approaches that promise to directly enable opinion-oriented information-seeking systems and focuses on methods that seek to address the new challenges raised by sentiment-aware applications, as compared to those that are already present in more traditional fact-based analysis.
Automatic construction of a context-aware sentiment lexicon: an optimization approach
This paper proposes a novel optimization framework that provides a unified and principled way to combine different sources of information for learning a context-dependent sentiment lexicon that is not only domain specific but also dependent on the aspect in context given an unlabeled opinionated text collection.
A Lexicon-Enhanced Method for Sentiment Classification: An Experiment on Online Product Reviews
As an emerging communication platform, Web 2.0 has led the Internet to become increasingly user-centric and opinion and sentiment information has become increasingly important for both service and product providers and users because it plays an important role in influencing consumer purchasing decisions.
Twitter mood predicts the stock market