Select Page
Multilingual social media post extraction

Multilingual Social Media post extraction for product relevancy and sentiment analysis – Case Study

About the client

A leading social media platform which is well-positioned to fulfil user’s needs.

Requirements:

Our client wanted us to establish a process with minimum human intervention for extracting the social media post on brand relevancy and sentiment associated with it in multiple locales which is influencing the consumer and companies as well by spreading useful information and exchange of positive, negative, or neutral values.

The Challenges:

Client wanted us to develop a tool with an interface to extract all the social media post relevant to a product and brand involved in the analysis. To categorize these, we need to set up an automation process to extract the social media post globally in multiple locales like Arabic, Swedish, Korean, and Indonesian. The greatest challenge was to identify the public tweets with hashtags based upon the keyword or product information provided by client for analysis.

Social media data analysis

The Solution:

Fidel analyzed the requirements and identified key areas which plays an important role in extracting multilingual social media post data and performs an analysis and categorization on extracted contents.

  1. We provide hybrid approach of Web scraping and Social Media streaming API.
  2. Python script with supports Python based modules.
  3. NLP and lexicon dictionary to identify language detection and sentiment classification on various data languages.

Based upon this analysis, Fidel laid out the flow to achieve this with easy use of technology and programming languages like Python and its supported modules like NLP and NumPy. 

Benefits:

We were able to categorize social media post to find out the brands presence and sentiment associated in the post.
We were able to deliver high-volume categorized data across multiple languages with identifying relevancy as “Relevant” or “Irrelevant” and sentiment as “Positive”, “Negative” and “Neutral”.

Result:

By categorizing social media posts, client can see where their brand is being mentioned and make better decisions. This information can be used to track brand awareness and engagement.