Social Media Analytics

• Text Analysis/Mining
Support researchers to find inferences from
texts.
In this classification of text on the basis of
sentiment is sentiment analysis.
Two approaches:
a) Dictionary based classification
b) Machine learning based
• Social Network Analysis
Finds relationship between persons, groups by
analyzing structure of their connections.
Influence of an actor in network can be
determined.
• Trend Analysis is to make use of recent
advances to predict emerging topics.
 Explore & Evaluate-Dashboard
• Snapshot of social media activity from one
single source.
• Collection of widgets giving personnel an
overview of reports and metrics.
• Allow monitoring of any metrics and find
correlation between different reports.
 Dashboard-drill down capabilities
• Drill down business data into the level of
detail as needed.
• See What is causing trend
• What area business requires action
• Include more complex charts & graphs
 Types of charts
• Pie Chart
• Bar Chart
• Trend Chart
 Sentiment Analysis
• Sentiment analysis (or opinion mining) is a
natural language processing (NLP) technique used to determine whether
data is positive, negative or neutral.
• Sentiment analysis is often performed on textual data to help businesses
monitor brand and product sentiment in customer feedback, and
understand customer needs.
 Types of Sentiment Analysis
• Sentiment analysis focuses on the polarity of a text (positive, negative, neutral) but
it also goes beyond polarity to detect specific feelings and emotions (angry, happy,
sad, etc), urgency (urgent, not urgent) and even intentions (interested v. not
interested).
• Graded Sentiment Analysis
If polarity precision is important to your business, you might consider expanding your
polarity categories to include different levels of positive and negative
• Emotion detection
Emotion detection sentiment analysis allows you to go beyond polarity to detect
emotions, like happiness, frustration, anger, and sadness. Uses text and ML algos.
• Aspect-based Sentiment Analysis
Usually, when analyzing sentiments of texts you’ll want to know which particular
aspects or features people are mentioning in a positive, neutral, or negative way.
 Dashboard analysis of sentiment
four sentiment analysis data visualization results
that the dashboard has visualized for us.
• Overall Sentiment
• Sentiment over Time
• Sentiment by Rating
• Sentiment by Topic