狠狠撸

狠狠撸Share a Scribd company logo

Whatsapp analytics

?Download as PPTX, PDF?
?
D
Dipesh Patel

This document discusses analyzing WhatsApp group data from two business groups - Frugetory and White Gold - to gain insights. Data was collected from WhatsApp web using web scraping and analyzed using sentiment analysis, keyword extraction, and topic modeling. The analysis found that most posts in Frugetory were positive while most in White Gold were neutral. It also identified frequent words and topics in each group. The document proposes continuing this analysis could help businesses better understand customers and improve strategies.

1 of 27
Downloaded 11 times
WhatsApp Analytics
Objective More than 34 billion texts according to report are exchanged over the WhatsApp every day and if we could analyze and get valuable insights from this data and leverage it to not only take better real-time decisions but also add value to the stakeholders at much lower cost and time and hence align our operational efficiency with organizational strategy.
Data Source ? WhatsApp web:- https://web.whatsapp.com/ ? Below WhatsApp groups has been considered for analytics purpose ? Frugetory ? White Gold
Data Collection ? Data has been collected through web scrapping with python using below techniques:- ? Beautiful soup:-Beautiful Soup is a Python library for pulling data out of web ? Selenium:- Selenium is a open-source web-based automation tool
Methodology ? Following Text Based methods has been used:- 1. Sentiment Analysis 2. Keywords Extraction 3. Topic Modelling
Group I Analysis Period Considered:- 26thFeb-30thMay 2019
Group Description ? Frugetory group representatives comprise of Territory Managers, SBU’s head. ? Purpose of this group is to track our products sale and demonstration activities related to fruits and vegetables posted by users. ? Total 127 Participants in the group ? Group Created on March 2017 ? Type:-Business
Overall User Post Frequency
Media Vs. Text
Zone Wise Post Frequency
Overall User Post Activity By Territory 3.9% 3.9%
Post SBU Level
Territory Managers Media vs. Text Territory wise
Whatsapp analytics
Sentiment Score Note:- Pie Chart depicts 58 percent of times user chats are Positive.
Word Cloud Note:- From Above fig frequently typed words are highlighted.
Topic Modelling
Topic Terms
Group II Analysis Timeline Considered:- 10th April -28th May 2019
Group Description ? White Gold group representatives comprise of Territory managers, Zone managers. ? Purpose of this group is to track our products sale and demonstration activities related to cotton crop posted by users. ? Total 161 Participants in the group ? Group Created on June 2018 ? Type:-Business
User Activity
Media Vs. Text
User Post Representation By Territory 3.7% 3%
Word Cloud Note:- From Above fig frequently typed words are highlighted.
Sentiment Score Note:- Pie Chart depicts approx. 83 percent of times user chats are Neutral.
Scope ? It is an opportunity to build one-to-one communications and relationships with farming communities, business users while deep diving into their chat pattern. ? Chat interactions will also certainly help our stakeholders to better understand farmers requirements and align their strategy accordingly. ? Segment users accordingly with respect to their sentiment and help decision makers to identify loophole in process. ? Helps identify user behavior with according to type of content being share and saves time for stakeholders to keep tab on each messages manually. ? Using Analytics dashboard decision makers can view important topics, products feedback, query related to business process by eliminating redundancy
Next Step and Challenges ? Build Automated data fetching system and analytics engine for the same. ? To get insights from image and video data. ? Focus on advance ML areas.

More Related Content

Whatsapp analytics

  • 2. Objective More than 34 billion texts according to report are exchanged over the WhatsApp every day and if we could analyze and get valuable insights from this data and leverage it to not only take better real-time decisions but also add value to the stakeholders at much lower cost and time and hence align our operational efficiency with organizational strategy.
  • 3. Data Source ? WhatsApp web:- https://web.whatsapp.com/ ? Below WhatsApp groups has been considered for analytics purpose ? Frugetory ? White Gold
  • 4. Data Collection ? Data has been collected through web scrapping with python using below techniques:- ? Beautiful soup:-Beautiful Soup is a Python library for pulling data out of web ? Selenium:- Selenium is a open-source web-based automation tool
  • 5. Methodology ? Following Text Based methods has been used:- 1. Sentiment Analysis 2. Keywords Extraction 3. Topic Modelling
  • 6. Group I Analysis Period Considered:- 26thFeb-30thMay 2019
  • 7. Group Description ? Frugetory group representatives comprise of Territory Managers, SBU’s head. ? Purpose of this group is to track our products sale and demonstration activities related to fruits and vegetables posted by users. ? Total 127 Participants in the group ? Group Created on March 2017 ? Type:-Business
  • 8. Overall User Post Frequency
  • 10. Zone Wise Post Frequency
  • 11. Overall User Post Activity By Territory 3.9% 3.9%
  • 13. Territory Managers Media vs. Text Territory wise
  • 15. Sentiment Score Note:- Pie Chart depicts 58 percent of times user chats are Positive.
  • 16. Word Cloud Note:- From Above fig frequently typed words are highlighted.
  • 19. Group II Analysis Timeline Considered:- 10th April -28th May 2019
  • 20. Group Description ? White Gold group representatives comprise of Territory managers, Zone managers. ? Purpose of this group is to track our products sale and demonstration activities related to cotton crop posted by users. ? Total 161 Participants in the group ? Group Created on June 2018 ? Type:-Business
  • 23. User Post Representation By Territory 3.7% 3%
  • 24. Word Cloud Note:- From Above fig frequently typed words are highlighted.
  • 25. Sentiment Score Note:- Pie Chart depicts approx. 83 percent of times user chats are Neutral.
  • 26. Scope ? It is an opportunity to build one-to-one communications and relationships with farming communities, business users while deep diving into their chat pattern. ? Chat interactions will also certainly help our stakeholders to better understand farmers requirements and align their strategy accordingly. ? Segment users accordingly with respect to their sentiment and help decision makers to identify loophole in process. ? Helps identify user behavior with according to type of content being share and saves time for stakeholders to keep tab on each messages manually. ? Using Analytics dashboard decision makers can view important topics, products feedback, query related to business process by eliminating redundancy
  • 27. Next Step and Challenges ? Build Automated data fetching system and analytics engine for the same. ? To get insights from image and video data. ? Focus on advance ML areas.