{"id":21626293,"url":"https://github.com/jung217/lstm_bert_sentiment_analysis","last_synced_at":"2025-10-05T03:17:23.006Z","repository":{"id":171261745,"uuid":"647657856","full_name":"Jung217/LSTM_BERT_Sentiment_Analysis","owner":"Jung217","description":"基於LSTM\u0026BERT機器學習之網路輿情分析","archived":false,"fork":false,"pushed_at":"2023-05-31T12:32:02.000Z","size":59102,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-24T22:42:23.003Z","etag":null,"topics":["ai","analysis","bert","lstm","machine-learning","network","shopee","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/Jung217.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-05-31T08:49:20.000Z","updated_at":"2024-01-08T11:37:43.000Z","dependencies_parsed_at":null,"dependency_job_id":"e1f8795c-74eb-4006-9c09-3eebdbb5553d","html_url":"https://github.com/Jung217/LSTM_BERT_Sentiment_Analysis","commit_stats":null,"previous_names":["jung217/lstm_bert_sentiment_analysis"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jung217%2FLSTM_BERT_Sentiment_Analysis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jung217%2FLSTM_BERT_Sentiment_Analysis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jung217%2FLSTM_BERT_Sentiment_Analysis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jung217%2FLSTM_BERT_Sentiment_Analysis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Jung217","download_url":"https://codeload.github.com/Jung217/LSTM_BERT_Sentiment_Analysis/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244297972,"owners_count":20430362,"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":["ai","analysis","bert","lstm","machine-learning","network","shopee","tensorflow"],"created_at":"2024-11-25T01:12:53.614Z","updated_at":"2025-10-05T03:17:17.945Z","avatar_url":"https://github.com/Jung217.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Network Sentiment Analysis Based on LSTM \u0026 BERT Machine Learning\n### 基於 LSTM \u0026amp; BERT 機器學習之網路輿情分析\n\n\u003e 「縱浪大化中，不喜亦不懼。應盡便須盡，無復獨多慮。」－陶淵明〈神釋〉\n\n\u003e 「AI科技發展快速，其無非是世界一道不可阻攔的洪流，人們應保持開放樂見的心態面對，在一波波的浪潮中，尋等機會，一舉站上AI的浪頭上，盡享AI帶來的便利及紅利。」－CCJ\n\n## Preface\n本專案為紀念2023年5月，整個月不捨晝夜訓練模型的我，跟訓練AI模型差點成為Colab Pro的我，僅此。\n\u003cbr/\u003e\n\n## Introduction\n* [Detail Report](https://github.com/Jung217/LSTM_BERT_Sentiment_Analysis/blob/main/Network%20Sentiment%20Analysis%20Based%20on%20LSTM%20%26%20BERT%20Machine%20Learning_By_CCJ.pdf) : All the details about this project\n* [LSTM Model](https://github.com/Jung217/LSTM_BERT_Sentiment_Analysis/tree/main/LSTM)\n    * [LSTM.ipynb](https://github.com/Jung217/LSTM_BERT_Sentiment_Analysis/blob/main/LSTM/LSTM.ipynb) : Main training and testing program \n    * [input](https://github.com/Jung217/LSTM_BERT_Sentiment_Analysis/tree/main/LSTM/input)\n        * [apply-jieba-tokenizer](https://github.com/Jung217/LSTM_BERT_Sentiment_Analysis/tree/main/LSTM/input/apply-jieba-tokenizer) : Tokenizer and testing data \n        * [fake-news-pair-classification-challenge](https://github.com/Jung217/LSTM_BERT_Sentiment_Analysis/tree/main/LSTM/input/fake-news-pair-classification-challenge) : Origin training data\n* [BERT Model](https://github.com/Jung217/LSTM_BERT_Sentiment_Analysis/tree/main/BERT)\n    * [BERT.ipynb](https://github.com/Jung217/LSTM_BERT_Sentiment_Analysis/blob/main/BERT/BERT.ipynb) : Main training and testing program\n    * [commentss.csv](https://github.com/Jung217/LSTM_BERT_Sentiment_Analysis/blob/main/BERT/commentss.csv) : Training, Testing and validation data\n* [Shopee Crawler(蝦皮爬蟲程式)](https://github.com/Jung217/LSTM_BERT_Sentiment_Analysis/tree/main/Shopee%20Crawler) \n    * [shopee.ipynb](https://github.com/Jung217/LSTM_BERT_Sentiment_Analysis/blob/main/Shopee%20Crawler/shopee.ipynb) : Crawler program to get data from [Shopee](https://shopee.tw/)\n    * [Data](https://github.com/Jung217/LSTM_BERT_Sentiment_Analysis/tree/main/Shopee%20Crawler/Data) : Commodity data from shopee\n\n## Reference\n1. [Kaggle-WSDM - Fake News Classification](https://www.kaggle.com/competitions/fake-news-pair-classification-challenge)\n\n2. [LeeMeng:進擊的 BERT：NLP 界的巨人之力與遷移學習](https://leemeng.tw/attack_on_bert_transfer_learning_in_nlp.html)\n\n3. [Evaluation Metrics : 分類模型](https://medium.com/ai%E5%8F%8D%E6%96%97%E5%9F%8E/evaluation-metrics-%E5%88%86%E9%A1%9E%E6%A8%A1%E5%9E%8B-ba17ad826599)\n\n4. [「蝦皮爬蟲」｜商品資料＋留言評論](https://marketingliveincode.com/classification/crawler_king/110)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjung217%2Flstm_bert_sentiment_analysis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjung217%2Flstm_bert_sentiment_analysis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjung217%2Flstm_bert_sentiment_analysis/lists"}