Select Page
Multilingual Sentiment Analysis of Social Media Data Extraction

Multilingual Sentiment Analysis of Social Media Data Extraction – Case Study

About the client

A leading social media company which has revolutionized the way we all purchase goods utilizing cloud technology and Automatic Speech Recognition.

Requirements :

Our client wanted us to establish a process with minimum human intervention for categorizing social media posts based on brand relevancy and sentiment associated with it, that would save time and resources.

Project details:

Service: Software Development
Source language: English
Target language: German, French, Spanish, and Japanese.
Tools and technology used:  Python

Challenges :

Our client wanted us to create a tool that would collect all social media posts relevant to a specific product and brand. The tool would need to be able to extract posts from multiple languages like, German, French, Spanish, and Japanese . These posts would then be categorized according to their relevance and sentiment.

Solution :

Fidel analyzed the requirements for extracting social media data and categorizing its contents. He identified key areas that play an important role in this process, including:

  • Using Python to create a Graphical User Interface that supports AI modules.
  • Using natural language processing (NLP) to identify language detection and classification on various target languages.

Based on this analysis, Fidel laid out a flow to achieve audio signal processing using technology and programming languages like Python and its NumPy library. This flow makes it easy to use NLP to process audio signals.


Result :

  • Fidel was able to classify the speech and non-speech segments and introduce quality checks on the transcribed data.
  • Our solution effectively process their audio data while identifying and classifying the contents, which is vital to train their Automatic Speech Recognition engines.
  • We were able to deliver high-volume transcribed data across multiple languages, which saved the client time and resources, and increased customer satisfaction by better understanding customer sentiment.