Context

Social Media has been taking up everything on the Internet. People getting the latest news, useful resources, life partner and what not. In a world where Social media plays a big role in giving news, we must also know that news which affects our sentiments are going to get spread like a wildfire. Based on the Headline and the title, and according to the date given and the Social media platforms, you have to predict how it has affected the human sentiment scores. You have to predict the column “SentimentTitle” and “SentimentHeadline”.

Content

This is a subset of the dataset of the same name available in the UCI Machine Learning Repository The collected data relates to a period of 8 months, between November 2015 and July 2016, accounting for about 100,000 news items on four different topics: economy, microsoft, obama and palestine.

Dataset Information

The attributes for each of the dataset are :

• IDLink (numeric): Unique identifier of news items
• Title (string): Title of the news item according to the official media sources
• Headline (string): Headline of the news item according to the official media sources
• Source (string): Original news outlet that published the news item
• Topic (string): Query topic used to obtain the items in the official media sources
• Publish-Date (timestamp): Date and time of the news items' publication
• Facebook (numeric): Final value of the news items' popularity according to the social media source Facebook
• Google-Plus (numeric): Final value of the news items' popularity according to the social media source Google+
• LinkedIn (numeric): Final value of the news items' popularity according to the social media source LinkedIn
• SentimentTitle: Sentiment score of the title, Higher the score, better is the impact or +ve sentiment and vice-versa. (Target Variable 1)
• SentimentHeadline: Sentiment score of the text in the news items' headline. Higher the score, better is the impact or +ve sentiment. (Target Variable 2)