explaingit

viwaz/sentiment_analysis

Analysis updated 2026-07-17

★ 1Jupyter NotebookAudience · researcherComplexity · 3/5Setup · moderate

TLDR

A sentiment analysis tool for Facebook comments in a low-resource, code-switched language, comparing simple and neural network models.

Mindmap

mindmap
  root((repo))
    What it does
      Detects comment sentiment
      Handles mixed languages
      Keeps emojis intact
    Tech stack
      Python
      Jupyter Notebook
      AfriBERTa
      Apify
    Use cases
      Monitor public opinion
      Score scraped comments
      Serve predictions via API
    Audience
      Researchers
      Data scientists
      Organizations

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Monitor Facebook discussions about a public health campaign or political issue at scale.

USE CASE 2

Automatically score newly scraped comments for sentiment instead of reading them manually.

USE CASE 3

Compare a simple TF-IDF model against a neural network model to pick the best performer.

USE CASE 4

Run the trained model as a web API service serving live predictions.

What is it built with?

PythonJupyter NotebookAfriBERTaTF-IDFApify

How does it compare?

viwaz/sentiment_analysisandy1li/udacity-reinforcementcynikolai/sequence-cluster-learner
Stars111
LanguageJupyter NotebookJupyter NotebookJupyter Notebook
Last pushed—2021-05-132017-12-02
Maintenance—DormantDormant
Setup difficultymoderatemoderateeasy
Complexity3/53/51/5
Audienceresearcherresearchergeneral

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 1h+

Requires Apify access for scraping and understanding of the notebook-based data science workflow.

Copy-paste prompts

Prompt 1
Explain how this project handles code-switched, low-resource language comments during preprocessing.
Prompt 2
Help me set up the Apify scraping step to collect Facebook comments for this pipeline.
Prompt 3
Show me how to call the web API this project exposes for sentiment predictions.
Prompt 4
Walk me through comparing the TF-IDF model against the AfriBERTa model in this project.

Frequently asked questions

What is sentiment_analysis?

A sentiment analysis tool for Facebook comments in a low-resource, code-switched language, comparing simple and neural network models.

What language is sentiment_analysis written in?

Mainly Jupyter Notebook. The stack also includes Python, Jupyter Notebook, AfriBERTa.

How hard is sentiment_analysis to set up?

Setup difficulty is rated moderate, with roughly 1h+ to a first successful run.

Who is sentiment_analysis for?

Mainly researcher.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.

Alternatives & similar repos