Skip to content

Aspect based sentiment analysis aims to detect an aspect (i.e. features) in a given text and then perform sentiment analysis of the text with respect to that aspect. This project aims to give a solution for the FiQA 2018 challenge subtask 1.

Notifications You must be signed in to change notification settings

ashishsalunkhe/Aspect-based-Financial-Sentiment-Analysis

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 

Repository files navigation

Aspect-based-Financial-Sentiment-Analysis

Aspect based sentiment analysis aims to detect an aspect (i.e. features) in a given text and then perform sentiment analysis of the text with respect to that aspect. This project aims to give a solution for the FiQA 2018 challenge subtask 1.

Given a text instance in the financial domain (microblog message, news statement or headline) in English, detect the target aspects which are mentioned in the text (from a pre-defined list of aspect classes) and predict the sentiment score for each of the mentioned targets. Sentiment scores will be defined using continuous numeric values ranged from -1(negative) to 1(positive).

Model is evaluated on the basis of precision, recall and F1-score for aspect classification approaches and regard to MSE and R Squared(R^2) metrics for sentiment prediction.

An example of the input/output of the task is defined below:

"55": {

"sentence": "Tesco Abandons Video-Streaming Ambitions in Blinkbox Sale", 

"info": [ 

  { 

    "snippets": "['Video-Streaming Ambitions']", 

    "target": "Blinkbox", 

    "sentiment_score": "-0.195", 

    "aspects": "['Corporate/Stategy']" 

  }, 

  { 

    "snippets": "['Tesco Abandons Video-Streaming Ambitions ']", 

    "target": "Tesco", 

    "sentiment_score": "-0.335", 

    "aspects": "['Corporate/Stategy']" 

  } 

] 

}

If you happen to refer my work please cite our research paper: Link

BibTeX Cite:

@article{salunkhe2019aspect, title={Aspect based sentiment analysis on financial data using transferred learning approach using pre-trained BERT and regressor model”}, author={Salunkhe, Ashish and Mhaske, Shubham}, year={2019} }

About

Aspect based sentiment analysis aims to detect an aspect (i.e. features) in a given text and then perform sentiment analysis of the text with respect to that aspect. This project aims to give a solution for the FiQA 2018 challenge subtask 1.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published