/Pundits-Review-Sentiment-Prediction

Development of the prediction model for the Pundits Review website used to predict the sentiment in football news articles - https://www.punditsreview.com/

Primary LanguageJupyter Notebook

Pundits Review Sentiment Prediction

Development of the prediction model for the Pundits Review website used to predict the sentiment in football news articles - https://www.punditsreview.com/

Pundits Review scrapes and processes news articles about the Premier League in order to give players and teams a review score each week. Each Monday, the project collects articles, divides them into phrases, identifies the player or club being referred to and then predicts the sentiment of the phrase. See more on how it works here!

About this repository

This repository shows the progression of the methods used to train a model to predict the sentiment of phrases within a football news article. Attempts 1 & 2 use general sentiment datasets whereas 'Building the model' uses football specific sentiment data from BetSentiment.com. My final training data is provided alongside the methods used to pre-process it.

Contents

Attempt 1

Attempt 1 trains a Linear Regression sentiment model on a twitter sentiment dataset provided by Stamford University

Attempt 2

Attempt 2 trains a Linear Regression sentiment model on a airlines sentiment dataset - Kaggle

Building the Model

Notebook used to build different models using BetSentiment data

Evaluating Approaches

Notebook used to compare accuracy scores & confusion matrix between 48 approaches to predicting sentiment. Visualisations included.

Preprocessing

Notebook used to clean and preprocess the training data

Annotated Data

Manually annotated (sentiment & player target) set of 500 rows of sample data taken from The Mirror - Match Reports

Training Data

Training data used to train different model approaches in 'Building_the_model' - After preprocessing

Associated Repositories

Pundits Review - 11/09/2020 - Complete directory for Pundits Review web application.
Resources - Data, images & Python dictionary of Premier League players & teams
Scraping - Development of the scraping process used to collect data
Entity Extraction - Development of the process used to recognise Premier League player & club entities within a news article

Any Questions ... Send me an email!