University of Illinois Urbana-Champaign

TED Talks – A Predictive Analysis Using Classification Algorithms

Paulami Ray; Kumkum Yadav; Garima Garg

Permalink

https://hdl.handle.net/2142/99922

Description

Title
TED Talks – A Predictive Analysis Using Classification Algorithms
Author(s)
  • Paulami Ray
  • Kumkum Yadav
  • Garima Garg
Issue Date
2018-04-24
Keyword(s)
  • Classification algorithms
  • Machine learning
  • Data Mining
  • Logistic Regression
  • Support Vector Machine
  • KNN
  • Naive Bayes
Abstract
TED talks are a great source of knowledge and ideas which are available online for free. TED talk encompasses a plethora of topics like Technology, Entertainment, Design, Cultural, Academic Research etc. which are presented by different speakers. The purpose of this study is to develop a model to predict two things – firstly, to predict the number of views for the talks and secondly, to predict the overall reaction of the talks from the description of the comments given by the users. We have used several machine learning classification algorithms like SVM, Logistic Regression, Random Forest, Decision tree and KNN. The dataset for this project includes details of 2550 TED Talks from 2006 to 2017. We have also done some visualizations on the data set to get more understanding of the topic and analyze it further.
Publisher
University of Illinois at Urbana-Champaign School of Information Sciences
Type of Resource
other
Language
en
Permalink
http://hdl.handle.net/2142/99922
Sponsor(s)/Grant Number(s)
University of Illinois at Urbana-Champaign School of Information Sciences

Owning Collections

Illinois Research and Scholarship (Open Collection) PRIMARY
This is the default collection for all research and scholarship developed by faculty, staff, or students at the University of Illinois at Urbana-Champaign