{"id":15105297,"url":"https://github.com/mizuhara1314/livechat_sentiment_analysis_web","last_synced_at":"2026-01-29T00:06:03.459Z","repository":{"id":256570417,"uuid":"855781854","full_name":"mizuhara1314/LiveChat_sentiment_analysis_web","owner":"mizuhara1314","description":"大四單人畢設，基於bert_lstm模型的直播實時情感分析網站","archived":false,"fork":false,"pushed_at":"2024-11-24T13:10:45.000Z","size":82,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-25T11:11:22.066Z","etag":null,"topics":["flask"],"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/mizuhara1314.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,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-09-11T13:05:59.000Z","updated_at":"2024-11-24T13:10:49.000Z","dependencies_parsed_at":"2024-11-24T15:15:24.802Z","dependency_job_id":null,"html_url":"https://github.com/mizuhara1314/LiveChat_sentiment_analysis_web","commit_stats":{"total_commits":17,"total_committers":2,"mean_commits":8.5,"dds":0.05882352941176472,"last_synced_commit":"d571d169656b4a8ca943c70b392e00796f45a433"},"previous_names":["mizuhara1314/livechat_sentiment_analysis_web"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mizuhara1314%2FLiveChat_sentiment_analysis_web","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mizuhara1314%2FLiveChat_sentiment_analysis_web/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mizuhara1314%2FLiveChat_sentiment_analysis_web/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mizuhara1314%2FLiveChat_sentiment_analysis_web/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mizuhara1314","download_url":"https://codeload.github.com/mizuhara1314/LiveChat_sentiment_analysis_web/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248429062,"owners_count":21101780,"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":["flask"],"created_at":"2024-09-25T20:23:05.867Z","updated_at":"2026-01-29T00:06:03.454Z","avatar_url":"https://github.com/mizuhara1314.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 1. 簡介：\n  使用之前訓練好的bert_lstm情感模型來實時預測yt跟twitch直播間的觀眾情緒，更新間格為10秒，測試文本在upload的test.txt裡\n# 2. 效果：\n\n\n\n\n\n\n\nhttps://github.com/user-attachments/assets/4375435d-bafa-4060-b62d-2ee9b7b90a6b\n\n\n\n\n\n![螢幕擷取畫面 2024-09-11 205640](https://github.com/user-attachments/assets/4cb232b9-9376-4e83-b908-1091bdf1a8f1)\n\n\u003cimg width=\"462\" height=\"368\" alt=\"螢幕擷取畫面 2026-01-07 155303\" src=\"https://github.com/user-attachments/assets/68888ba2-cf01-4f80-a38f-c6db9355f1da\" /\u003e\n\n\n\n# 3. 運行項目：\n\n### 注意事項 ###\n先至anaconda3\\Lib\\site-packages\\pytchat\\core文件夾下的pytchat.py中删除这一部分代码(否則會出現\"signal only works in main thread of the main interpreter\")\n\n```bash\n\nif interruptable:\n    signal.signal(signal.SIGINT, lambda a, b: self.terminate())\n\n```\n\n然後至 https://drive.google.com/file/d/1lnJuSLQKl6Xi-o9SYQ3hwElazgswvjKf/view?usp=sharing 下載模型，並解壓到項目根目錄下讓app.py讀取\n然後在工作環境選擇conda interpreter\n\n在 Flask 後端項目下運行後端代碼：\n\n```bash\npython app.py  \n```\n會運行在本機port 7000\n\n或是\n```bash\npython -m flask run\n```\n\n會默認運行在port 5000\n\n然後在瀏覽器開啟localhost即可：\n# 4. 缺點：\n\n載入模型功能模塊時無法讀取bert_classfier類(動態連結問題?)，得加個setattr()解決這bug\n\n# 5. 改進\n未來可以使用像kafka之類的實時流數據框架或者類似c#的sinalR/websocket通訊來取代ajax/axios需要定時輪循達成監聽\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmizuhara1314%2Flivechat_sentiment_analysis_web","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmizuhara1314%2Flivechat_sentiment_analysis_web","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmizuhara1314%2Flivechat_sentiment_analysis_web/lists"}