{"id":20435491,"url":"https://github.com/jacksonchen1998/chinese-dimensional-sentiment-analysis","last_synced_at":"2026-04-19T01:37:54.411Z","repository":{"id":238273971,"uuid":"786695816","full_name":"jacksonchen1998/Chinese-dimensional-sentiment-analysis","owner":"jacksonchen1998","description":"2024 NYCU Natural Language Processing","archived":false,"fork":false,"pushed_at":"2024-05-14T06:04:27.000Z","size":572,"stargazers_count":1,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-12-09T13:03:56.780Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/jacksonchen1998.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}},"created_at":"2024-04-15T06:08:41.000Z","updated_at":"2024-05-30T04:26:46.000Z","dependencies_parsed_at":"2024-05-14T07:26:17.316Z","dependency_job_id":"e4349765-7678-48fb-88d1-6a8ea986dfcc","html_url":"https://github.com/jacksonchen1998/Chinese-dimensional-sentiment-analysis","commit_stats":null,"previous_names":["jacksonchen1998/chinese-dimensional-sentiment-analysis"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jacksonchen1998/Chinese-dimensional-sentiment-analysis","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacksonchen1998%2FChinese-dimensional-sentiment-analysis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacksonchen1998%2FChinese-dimensional-sentiment-analysis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacksonchen1998%2FChinese-dimensional-sentiment-analysis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacksonchen1998%2FChinese-dimensional-sentiment-analysis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jacksonchen1998","download_url":"https://codeload.github.com/jacksonchen1998/Chinese-dimensional-sentiment-analysis/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacksonchen1998%2FChinese-dimensional-sentiment-analysis/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31991720,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-18T20:23:30.271Z","status":"ssl_error","status_checked_at":"2026-04-18T20:23:29.375Z","response_time":103,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":[],"created_at":"2024-11-15T08:34:51.635Z","updated_at":"2026-04-19T01:37:54.391Z","avatar_url":"https://github.com/jacksonchen1998.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Chinese-dimensional-sentiment-analysis\n2024 NYCU Natural Language Processing\n\n## Method\n\nThis method aims to leverage a set of six independently trained BERT-based models, each specializing in a different category. \n\nThe final prediction is derived from the average of all model outputs, providing a robust and reliable estimate.\n\n## Evaluation\n\nMean Absolute Error (MAE):\n\n$$\n  MAE = \\frac{1}{n} \\sum_{i=1}^n |a_i - p_i|\n$$\n\nPerson Correlation Coefficient ($r$):\n\n$$\n  r = \\frac{1}{n-1} \\sum_{i}^n (\\frac{a_i - \\mu_A}{\\sigma_A})(\\frac{p_i - \\mu_P}{\\sigma_A})\n$$\n\n- $a_i \\in A$: $i$-th actual value\n- $p_i \\in P$: $i$-th predicted value\n- $\\mu$: mean value\n- $\\sigma$: standard deviation\n- $n$: the number of test sample\n\nA lower MAE and a higher r indicate more accurate prediction performance.\n\n## Experiment\n\n### Dataset\n\n- Training Dataset: Chinese EmoBank (CVAT)\n- Testing Dataset: 1000+ Mental Health Texts\n\n### On Chinese EmoBank (CVAT) with Bert\n\n\u003ccenter\u003e\n  \u003ctable\u003e\n    \u003ctr\u003e\n      \u003cth\u003e\n        Method\n      \u003c/th\u003e\n      \u003cth\u003e\n        MAE\n      \u003c/th\u003e\n      \u003cth\u003e\n        r\n      \u003c/th\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n      \u003ctd\u003e\n        Valence\n      \u003c/td\u003e\n      \u003ctd\u003e\n        0.3342\n      \u003c/td\u003e\n      \u003ctd\u003e\n        0.95883\n      \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n      \u003ctd\u003e\n        Arousal\n      \u003c/td\u003e\n      \u003ctd\u003e\n        0.36525\n      \u003c/td\u003e\n      \u003ctd\u003e\n        0.88947\n      \u003c/td\u003e\n    \u003c/tr\u003e\n  \u003c/table\u003e\n\u003c/center\u003e\n\n\u003e Valence\n\n![bert_v_mae](./image/bert_v_mae.png)\n\n![bert_v_r](./image/bert_v_r.png)\n\n\u003e Arousal\n\n![bert_a_mae](./image/bert_a_mae.png)\n\n![bert_a_r](./image/bert_a_r.png)\n\n### On private dataset with Bert\n\n\u003ccenter\u003e\n  \u003ctable\u003e\n    \u003ctr\u003e\n      \u003cth\u003e\n        Method\n      \u003c/th\u003e\n      \u003cth\u003e\n        MAE\n      \u003c/th\u003e\n      \u003cth\u003e\n        r\n      \u003c/th\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n      \u003ctd\u003e\n        Valence\n      \u003c/td\u003e\n      \u003ctd\u003e\n        0.75\n      \u003c/td\u003e\n      \u003ctd\u003e\n        0.68\n      \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n      \u003ctd\u003e\n        Arousal\n      \u003c/td\u003e\n      \u003ctd\u003e\n        1.1\n      \u003c/td\u003e\n      \u003ctd\u003e\n        0.47\n      \u003c/td\u003e\n    \u003c/tr\u003e\n  \u003c/table\u003e\n\u003c/center\u003e\n\n### On Chinese EmoBank (CVAT) with MoE Bert\n\n### On private dataset with MoE Bert\n\n## Reference\n\n- [bert-base-chinese](https://huggingface.co/google-bert/bert-base-chinese)\n- [Chinese EmoBank: Building Valence-Arousal Resources for Dimensional Sentiment Analysis](https://dl.acm.org/doi/full/10.1145/3489141)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjacksonchen1998%2Fchinese-dimensional-sentiment-analysis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjacksonchen1998%2Fchinese-dimensional-sentiment-analysis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjacksonchen1998%2Fchinese-dimensional-sentiment-analysis/lists"}