ITECH1103 Big Data Analytics: YouTube Video Analysis Report 2018

This report analyzes a YouTube dataset from 2006 to 2018 using IBM Watson Analytics to identify trends and insights. The analysis explores various video attributes such as category, publish date, views, likes, and dislikes to provide recommendations for content managers. Key findings include identifying popular video categories, trends in video uploads across different countries, and factors contributing to video dislikes. The report concludes with suggestions for improving video quality and user engagement to maximize viewership and minimize negative feedback. Visualizations and graphs generated from IBM Watson are included to support the analysis. Desklib provides access to this and similar assignments for students.

Name of the Student:
Name of the university:

The requirement to use IBM Watson
The tool is a Business Intelligence tool which is used for
processing
An example is included here
Where was X born?
The birth place fo Einstien is included by the visualization.
Structured
Unstructu
red

A brief history of Watson
 Started in 2007,
 lead David Ferrucci
Initial goal: Natural
language processing
Knowledge Extraction
Need: Gathering
knowledge that would not
be possible by the usual
system.

Basic Architecture IBMBasic Architecture IBM
WatsonWatson

INTRODUCTION TO
CURRENT PROJECT
The selected dataset Youtube.xlsx contains the
information about different videos uploaded in the
period of 2006 to 2018. The data dictionary has the
following columns Video_id, Trending_date, Title,
Channel_title, Category_id, Publish_date, Time_frame,
Publish_day_of_week, Publish_country, Tags, Views,
Likes, Dislikes, Comments_count, Comments_disable,
Ratings_disabled, Video_error_or_removed. The
description of each columns are given in the question
file.

ADVANCED INSIGHTS
The advanced insights have been developed after the
dashboards have been developed.
The main goal for the insights are that they would be
able to provide the organizations with useful in
information so that they would be able to use it for
future endeavours.
The YouTube dataset has been used here for the
development of the insights on the topic and the
insights on dislikes have been developed here.

INSIGHT 1

INSIGHT 2

INSIGHT 3

INSIGHT 4

INSIGHT 5

RESEARCH
From the analysis it is found that, the
dataset contains data only about 18
categories which are listed below;
 1-Film & Animation
 10- Music
 29 – Non-profits & Activism
 20 – Gaming
 22 - People & Blogs
 23 – Comedy
 43 - Shows
 44 - Trailers
 24 - Entertainment
 22 - People & Blogs
 23 – Comedy
From the analysis it is found that, the
dataset contains data only about 18
categories which are listed below;
 43 - Shows
 44 - Trailers
 15 - Pets & Animals
 17 – Sports
 25 - News & Politics
 19 - Travel & Events
 26 – How to & Style
 2 Autos & Vehicles
 27 - Education
 28 - Science & Technology
 30 – Movies