{"id":23047333,"url":"https://github.com/aurelienmorgan/french_text_sentiment","last_synced_at":"2026-04-02T18:53:21.793Z","repository":{"id":236245434,"uuid":"294146650","full_name":"aurelienmorgan/french_text_sentiment","owner":"aurelienmorgan","description":"Sentiment Analysis in texts written in French language using Tensorflow/Keras (and using XGBoost for hyperparameters optimization)","archived":false,"fork":false,"pushed_at":"2020-09-09T15:03:19.000Z","size":22915,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-08T17:09:32.344Z","etag":null,"topics":["beautifulsoup","dask","fasttext","french","gru","hyperparameters-optimization","jupyter-notebook","keras","multiprocessing","nlp","python","rnn","scikit-learn","sentiment-analysis","tensorflow","transfer-learning","web-scraping","xgboost"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aurelienmorgan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2020-09-09T15:02:33.000Z","updated_at":"2024-12-07T17:58:53.000Z","dependencies_parsed_at":"2024-04-26T09:37:40.444Z","dependency_job_id":null,"html_url":"https://github.com/aurelienmorgan/french_text_sentiment","commit_stats":null,"previous_names":["aurelienmorgan/french_text_sentiment"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aurelienmorgan%2Ffrench_text_sentiment","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aurelienmorgan%2Ffrench_text_sentiment/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aurelienmorgan%2Ffrench_text_sentiment/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aurelienmorgan%2Ffrench_text_sentiment/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aurelienmorgan","download_url":"https://codeload.github.com/aurelienmorgan/french_text_sentiment/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246927808,"owners_count":20856193,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["beautifulsoup","dask","fasttext","french","gru","hyperparameters-optimization","jupyter-notebook","keras","multiprocessing","nlp","python","rnn","scikit-learn","sentiment-analysis","tensorflow","transfer-learning","web-scraping","xgboost"],"created_at":"2024-12-15T22:32:45.600Z","updated_at":"2025-12-30T22:50:59.151Z","avatar_url":"https://github.com/aurelienmorgan.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# French-Text Sentiment Analysis\n\n\n**Welcome to this project\u0026nbsp;!**\n\n\u003cp style=\"text-align: justify;\"\u003e\nThe topic covered here is Sentiment Analysis in texts written\n\u003cspan style=\"border-bottom:1px solid #000; text-decoration:underline; display:inline-block;\"\u003e\nin French language\u003c/span\u003e.\nFor that, we employ a Recurrent Neural Network that we build and run thru the Tensorflow / Keras framework.\n\u003cbr /\u003e\nThe architecture of the model is based on dual bi-directionnal GRU cells\nand it employs fastText word embeddings.\nWe train this model using tranfer learning from rated product reviews\nthat have been  web-scrapped using the BeautifulSoup python library\n\u003cfont style=\"color: darkgray;\"\u003e\u003cem\u003e(the web-scraping code is not provided,\nbut the collected data is)\u003c/em\u003e\u003c/font\u003e.\n\u003cbr /\u003e\n\u003cbr /\u003e\n\u003cimage style=\"margin: 0px 10px 0px 0px;\"  align=\"left\" src=\"./images/project_structure.png?uncahce=1234\" /\u003eThe figure on the left shows the structure of this project.\nThere are two key points to notice\u0026nbsp;:\n\u003cul style=\"line-height:22px\"\u003e\n\u003cli style=\"margin: 0px 0px 0px 300px;\"\u003eA dedicated custom python package named \u003cb\u003emy_NLP_RNN_fr_lib\u003c/b\u003e has been developped to serve this project.\u003c/li\u003e\n\u003cli style=\"margin: 0px 0px 0px 300px;\"\u003eThere's a whole sub-section to the herein project, detailled separately, on \u003cb\u003ehyperparameters optimization\u003c/b\u003e,.\nIt can be found \u003ca href=\"https://github.com/aurelienmorgan/french_text_sentiment/blob/master/model/optimization/\"\ntarget=\"_blank\"\u003ethere\u0026nbsp;\u003cimg\nhref='.' src='./images/target_blank.png' style='vertical-align: baseline; display: inline;' /\u003e\u003c/a\u003e.\nSpoiler alert\u0026nbsp;: we deal with random search first, then XGBoost + scikit-learn\nare called to get an extra edge.\n\u003c/li\u003e\n\u003c/ul\u003e\n\nThe French-Text Sentiment Analysis project we're dealing with here is explained in details and accompagnied with full running python code\nin a walkthrough Jupyter Notebook.\n\n\u003c/p\u003e\n\n\n\n\n\n\n\u003cdiv style=\"width: 100%;\"\u003e\n    \u003ccenter\u003e\n        \u003cdiv\u003e\n            \u003ca href=\"https://htmlpreview.github.io/?https://github.com/aurelienmorgan/french_text_sentiment/blob/master/main.html?uncache=654645\"\n                target=\"self\"\u003e\u003cimg alt=\"Jupyter Notebook\" src=\"./images/jupyter_notebook.png?uncache=1234\" height=\"40px\" /\u003e\u003c/a\u003e\n        \u003c/div\u003e\n    \u003c/center\u003e\n\u003c/div\u003e\n\u003cbr /\u003e\n\u003cbr /\u003e\n\n\n\n\nKEYWORDS :\n\t```Tensorflow```, ```Keras```,\n\t```GRU```, ```RNN```, ```NLP```, ```fastText```,\n\t```web-scraping```, ```BeautifulSoup```, \n\t```transfer learning```, ```french sentiment analysis```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faurelienmorgan%2Ffrench_text_sentiment","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faurelienmorgan%2Ffrench_text_sentiment","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faurelienmorgan%2Ffrench_text_sentiment/lists"}