{"id":13424839,"url":"https://github.com/Ermlab/pl-sentiment-analysis","last_synced_at":"2025-03-15T18:35:58.949Z","repository":{"id":33930979,"uuid":"140273801","full_name":"Ermlab/pl-sentiment-analysis","owner":"Ermlab","description":null,"archived":false,"fork":false,"pushed_at":"2022-11-22T02:20:08.000Z","size":24,"stargazers_count":27,"open_issues_count":6,"forks_count":10,"subscribers_count":10,"default_branch":"master","last_synced_at":"2024-10-26T23:55:46.705Z","etag":null,"topics":["deep-learning","polish-sentiment-analysis","word2vec"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Ermlab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2018-07-09T11:07:58.000Z","updated_at":"2022-09-06T18:54:41.000Z","dependencies_parsed_at":"2023-01-15T03:26:21.353Z","dependency_job_id":null,"html_url":"https://github.com/Ermlab/pl-sentiment-analysis","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ermlab%2Fpl-sentiment-analysis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ermlab%2Fpl-sentiment-analysis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ermlab%2Fpl-sentiment-analysis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ermlab%2Fpl-sentiment-analysis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Ermlab","download_url":"https://codeload.github.com/Ermlab/pl-sentiment-analysis/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243775932,"owners_count":20346290,"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":["deep-learning","polish-sentiment-analysis","word2vec"],"created_at":"2024-07-31T00:01:00.028Z","updated_at":"2025-03-15T18:35:53.927Z","avatar_url":"https://github.com/Ermlab.png","language":"Python","funding_links":[],"categories":["Datasets","Polish text datasets"],"sub_categories":["Task oriented datsets"],"readme":"# API for Polish sentiment analysis using Keras and Word2vec\n\nSentiment analysis is a natural language processing (NLP) problem where text is understood and the underlying intent\nis predicted.\n\nI will show you how you can predict the sentiment of Polish language texts as either positive, neutral or negative\nin Python using the Keras Deep Learning library and Google Word2vec.\n\nCheck Our blog post [Polish sentiment analysis using Keras and Word2vec](https://ermlab.com/en/blog/nlp/polish-sentiment-analysis-using-keras-and-word2vec/)\n\n## Getting started\n\n\n\nFirst of all you need to make sure you have installed Python 3.6. For that purpose we recommend Anaconda,\nit has all the necessary libraries except:\n* scikit-learn 0.19.1\n* Pandas 0.22.0\n* NumPy 1.14.0\n* Keras 2.1.4\n* gensim 3.4.0\n* many_stop_words 0.2.2\n* TensorFlow 1.6.0\n* wordcloud 1.4\n\nAll libraries can be installed with the following commands:\n\n```\npip install scikit-learn\npip install Keras\npip install gensim\npip install many_stop_words\npip install TensorFlow\npip install wordcloud\n```\n\nor quickly:\n```\npip install -r requirements.txt\n```\n\n\nOnce you have installed Python and the dependencies download at least [pre-trained Polish Word Embedding model](http://dsmodels.nlp.ipipan.waw.pl/dsmodels/nkjp+wiki-forms-all-100-cbow-hs.txt.gz) and extract\nto main project directory.\n\nThe easiest way to see our method in action is to run the LSTM.py script.\n\n## Data\n\nDownload our dataset from [Google Drive](https://drive.google.com/file/d/1vXqUEBjUHGGy3vV2dA7LlvBjjZlQnl0D/view?usp=sharing)\nand extract to /Data directory.\n\nOur dataset was collected from various sources:\n\n1. [Opineo](opineo.pl) - Polish service with all reviews from online shops\n2. Twitter - Polish current top hashtags from political news and Polish Election Campaign 2015\n3. [Polish Academy of Science HateSpeech project](http://zil.ipipan.waw.pl/HateSpeech)\n4. YouTube - comments from various videos\n\nDownload [Polish Word Embeddings from Polish Academy of Science](http://dsmodels.nlp.ipipan.waw.pl/w2v.html)\nand extract it in main folder.\n\n\n## Useful repos\n\n* https://github.com/Kyubyong/wordvectors, pre-trained word vector models for non-English languages\n* https://github.com/dakshitagrawal97/TweetSentimentAnalysis - jest zgoda!!\n* https://machinelearningmastery.com/predict-sentiment-movie-reviews-using-deep-learning/\n* http://dsmodels.nlp.ipipan.waw.pl/\n* https://github.com/BUPTLdy/Sentiment-Analysis\n* https://github.com/shayanzare007/EntitySentiment\n* https://github.com/Theo-/sentiment-analysis-keras-conv\n* https://github.com/giuseppebonaccorso/twitter_sentiment_analysis_word2vec_convnet\n* https://github.com/PAS43/TwitterSentimentAnalysis\n* https://github.com/kailashnathan\n* https://github.com/ankeshanand/review-helpfulness\n* https://github.com/spopov812/Sentiment-Analysis-Deep-Recurrent-Neural-Network-LSTM-\n* https://github.com/xingziye/movie-reviews-sentiment\n* https://github.com/dswald/sentiment_analysis/tree/0d6a85e4afef33eef5da7e6ac8aa2dbdb5e89de2\n* https://github.com/sukilau/amazon-sentiment-analysis\n\n\n## Contact \u0026 blog post\n\n* Main author: [Szymon Płotka](https://github.com/simongeek)\n* CEO of [Ermlab Software](https://ermlab.com) [Krzysztof Sopyła](https://github.com/ksopyla)\n* check Our blog post [Polish sentiment analysis using Keras and Word2vec](https://ermlab.com/en/blog/nlp/polish-sentiment-analysis-using-keras-and-word2vec/)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FErmlab%2Fpl-sentiment-analysis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FErmlab%2Fpl-sentiment-analysis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FErmlab%2Fpl-sentiment-analysis/lists"}