Scribd
Upload
411 views19 pages

M3-Social Media Text Analytics

Social media text analytics is used to analyze textual content from social media platforms. It can help understand user sentiment and opinions related to brands. There are two main types of social media text - static text like blogs which are longer and less frequently updated, and dynamic text like tweets which are short, diverse, and frequently changing. The main purposes of social media text analytics are sentiment analysis to classify text as positive/negative/neutral, intention mining to discover customer needs, trends mining to predict future events, and concept mining to extract ideas. Common steps involve data collection, text coding, analysis using tools like SPSS, and visualization of insights.

Uploaded by

KHAN SANA PARVEEN
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
411 views19 pages

M3-Social Media Text Analytics

Social media text analytics is used to analyze textual content from social media platforms. It can help understand user sentiment and opinions related to brands. There are two main types of social media text - static text like blogs which are longer and less frequently updated, and dynamic text like tweets which are short, diverse, and frequently changing. The main purposes of social media text analytics are sentiment analysis to classify text as positive/negative/neutral, intention mining to discover customer needs, trends mining to predict future events, and concept mining to extract ideas. Common steps involve data collection, text coding, analysis using tools like SPSS, and visualization of insights.

Uploaded by

KHAN SANA PARVEEN
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 19

3.

Social Media Text Analytics


Contents
● Social Media Text Analytics -
○ Types of Social Media Text
○ Purpose of Text Analytics
○ Steps in Text Analytics
○ Social Media Text Analysis Tools
Social Media Text Analytics
● Social media text analytics is a technique for extracting and analyzing
business insights from the textual content of social media platforms.
● It can be used to understand emotions and sentiments expressed in
user-generated content related to a brand or product.
● Text analytics has roots in various fields such as data mining and natural
language processing.
● It is useful for quickly and accurately understanding the vast volume of social
media content generated by users.
● Approximately 80% of data in organizations is textual, making text analytics
an important tool for business intelligence.
● e.g. Flyertalk.com
Types of Social Media Text
● Depending on nature of social media text , it can be classified as
○ Static Text
○ Dynamic Text
Static Text
● Static social media text is typically longer in length and updated or deleted
less frequently.
● Examples of static text include wiki content, blog pages, Word documents,
corporate reports, emails, and news transcripts.
● The purpose of static text is often to inform, educate, and elaborate on a
topic.
● Static text can provide valuable insights and information for businesses and
organizations.
Dynamic Text
● Dynamic text is real-time, user-generated text that expresses an opinion
about content or information on social media.
● It is typically shorter in length and diverse in nature, and is often updated or
deleted frequently.
● Examples of dynamic text include tweets, Facebook comments, and product
reviews.
● Dynamic text is often related to social, political, economic, personal, cultural,
or business issues and expresses the views and feelings of the user.
● Understanding dynamic text can provide valuable insights into the thoughts
and opinions of social media users.
Social Media Dynamic Text Examples:
● Social media text includes tweets, comments, discussions, conversations, and
reviews.
● Tweets are short messages (up to 140 characters) posted on Twitter, which may
include text, images, video, or links.
● Comments are written statements expressing opinions about content on social
media.
● Discussions take place through internet forums, which are organized by topic or
thread and allow users to post questions and replies.
● Conversations (or chatting) are instant exchanges of written messages between
two or more people, often through dedicated messaging tools. Most
conversations are private in nature.
● Reviews are evaluations of products or services by customers or experts, which
may include ratings and text. Product reviews can provide valuable insights into
customer opinions and feelings.
Purpose of Text Analytics
Sentiment Analysis
● Sentiment analysis involves categorizing social media text as positive,
negative, or neutral. It is often used to understand how customers feel about
a product, service, or issue.
● Tools like Semantria use algorithms to identify sentiment-bearing phrases in
text and assign them a score based on a logarithmic scale.
● Scores are then combined to determine the overall sentiment of a document
or sentence.
● Sentiment analysis can provide valuable insights into the emotions and
opinions of social media users.
Sentiment Analysis
● Step 1: It breaks the document into its basic parts of speech, called POS tags, which identify the
structural elements of a sentence (e.g. nouns, adjectives,verbs, and adverbs).
● Step 2: Algorithms identify sentiment-bearing phrases like “terrible service” or “cool atmosphere.”
● Step 3: Each sentiment-bearing phrase earns a score based on a logarithmic scale ranging from
negative ten to positive ten.
● Step 4: Next, the scores are combined to determine the overall sentiment of the document or
sentence. Document scores range between negative two and positive two. For example, to
calculate the sentiment of a phrase such as “terrible service,” Semantria uses search engine
queries similar to the following:
● “(Terrible service) near (good, wonderful, spectacular)” “(Terrible service) near (bad, horrible,
awful)”

● Each result is added to a hit count; these are then combined using a mathematical operation called
“log odds ratio” to determine the final score of a given phrase.
Intention Mining
● Intention mining involves discovering users' intentions (such as desire, wish,
or intention to buy) from natural language social media text.
● Companies can use intention mining to identify potential customers and
service existing customers who have issues with a product.
● Examples of intention-bearing phrases include "buy," "purchase," and "quit."
● Tools like Semantria can be used to mine intentions from social media text.
● Intention mining can provide valuable insights into the needs and desires of
social media users.
Trends Mining
● Trends mining, also known as predictive analytics, uses large amounts of
historical and real-time social media data to predict future events.
● It involves identifying patterns and trends in social media data to improve
products, services, or customer satisfaction.
● Techniques used in trends mining include machine learning, data mining, and
social network analysis.
● Predictive analytics using business data has been used in various industries,
but social media predictive analytics is still an emerging practice.
● Trends mining can provide valuable insights for businesses and
organizations looking to anticipate the needs and desires of their customers.
Concept Mining
● Concept mining is a method for extracting ideas and concepts from
documents.
● It is used to classify, cluster, and rank these ideas.
● Concept mining is different from text mining, which focuses on extracting
specific information rather than broader ideas and concepts.
● Examples of documents that can be analyzed using concept mining include
social media text, web pages, and news transcripts.
Steps in Text Analytics
Text Analytics Tools
● Discovertext: Discovertext (http://discovertext.com/) is a powerful platform for collecting, cleaning, and analyzing text and
social media data streams.

● Lexalytics: Lexalytics (http://www.lexalytics.com/) is a social media text and semantic analysis tool for social media
platforms, including Twitter, Facebook, blogs, etc.

● Tweet Archivist: Tweet Archivist (https://www.tweetarchivist.com/) is focused on searching, archiving, analyzing, and
visualizing tweets based on a search term
● or hashtag (#).

● Twitonomy: Twitonomy (https://www.twitonomy.com/) is a Twitter analytics tool for getting detailed and visual analytics on
tweets, retweets, replies, mentions, hashtags, followers, etc.

● Netlytic: Netlytic (https://netlytic.org) is a cloud-based text and social network analytics platform for social media text that
discovers social networks from online conversations on social media sites.

● LIWC: Linguistic Inquiry and Word Count (LIWC) is a text analysis tool for analyzing emotional, cognitive, structural, and
process components present in individuals’ verbal and written speech samples: http://www.liwc.net/

● Voyant: Voyant (http://voyant-tools.org/) is a web-based text reading and analysis. With Voyant, a body of text can be read
from a file or directly exported from a website.
Case Study
● FlyerTalk.com, is a company that specializes in products and services for
frequent travelers. The website features chat boards and discussions about
the latest travel information and loyalty programs for airlines and hotels.
● FlyerTalk.com wanted to analyze the large amount of customer feedback and
opinions expressed on their website.
● They used the SPSS software for analysis
● Data collection involved using web scraping techniques to crawl and scrape
the website for specific information, and store and screen scrape the data
into a structured format.
● Text coding and categorization involved assigning codes and categories to
the data to make it easier to analyze.
● Finally, text mining and visualization involved using statistical analysis and
visual representation of the data to draw insights and conclusions.F
Semantria detailed analysis report
Questions
● What is text analytics, and why it is useful?
● Differentiate between static and dynamic social media text.
● Discuss different social media texts.
● Explain the four main purposes of social media text analytics.
● Explain the typical social media text analysis steps.

● Tool - SPSS-https://www.ibm.com/account/reg/in-en/signup?formid=urx-19774
Thank You !!

You might also like