OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

French Sentiment Analysis With Bert

French Sentiment Analysis With Bert is an open-source research repository containing an Allociné movie-review sentiment dataset, notebook-based training code using CamemBERT and Transformers, and comparisons with other text-classification methods.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

French Sentiment Analysis With Bert — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a research starting point for binary French review classification, with dataset splits and multiple model comparisons in one repository.

Who it is for

  • Researchers comparing French sentiment-classification approaches.
  • Developers exploring a labeled French review dataset and notebook-based model training.
  • Readers studying model performance on movie reviews and selected cross-domain review data.

Documented uses

  • Explore positive and negative labels in a large French movie-review dataset.
  • Train and compare CamemBERT, TF-IDF, fastText, CNN and RNN approaches.
  • Review reported model results on Allociné reviews and selected Amazon review categories.
Before you choose

Requirements & limits

The repository is public and specifies an MIT license.

  • The dataset contains 200,000 positive and negative Allociné reviews, split into 160,000 training, 20,000 validation and 20,000 test examples.
  • Dataset files are described as JSONL and pickle.
  • The main BERT-based approach uses CamemBERT and Transformers.
  • Reported full-dataset results include 97.44% test accuracy and 97.34% test F1 for CamemBERT.
  • The README also reports inference results on French Amazon books, DVD and music review sets without additional training.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare the repository and open the BERT notebook

Install the project dependencies, extract the review dataset and open the documented BERT notebook.

Before you start

  • Git
  • Pipenv
  • Jupyter Notebook

Steps

  1. Clone the repository and change into its directory.

  2. Run pipenv install to install the project dependencies.

  3. Extract the dataset from allocine_dataset/data.tar.bz2.

  4. Run pipenv shell, then open 03_bert.ipynb with Jupyter Notebook.

Expected outcome

The documented environment is prepared and the BERT notebook is opened for experimentation.

Guide limitations

  • The instructions document setup and notebook opening, not the outcome of executing training.
  • The repository points readers needing inference to a separate Hugging Face integration section.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
TheophileBlard/french-sentiment-analysis-with-bert · Official homepage title · retained in its source language
How we review sourcesSuggest a correction