{"id":46468758,"url":"https://github.com/ayusrjn/ensemble-customer-analyzer","last_synced_at":"2026-03-06T06:00:05.149Z","repository":{"id":275192373,"uuid":"925352637","full_name":"ayusrjn/ensemble-customer-analyzer","owner":"ayusrjn","description":"Advanced RoBerta and DistillBert Based Abstract Based Sentiment Analyzer. Ensemble Architecture","archived":false,"fork":false,"pushed_at":"2025-01-31T19:16:24.000Z","size":0,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-31T19:28:45.308Z","etag":null,"topics":["distillbert-model","ensemble","roberta-base","setfit-absa"],"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/ayusrjn.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":"2025-01-31T18:03:15.000Z","updated_at":"2025-01-31T19:18:46.000Z","dependencies_parsed_at":"2025-01-31T19:38:52.490Z","dependency_job_id":null,"html_url":"https://github.com/ayusrjn/ensemble-customer-analyzer","commit_stats":null,"previous_names":["ayusrjn/ensemble-customer-analyzer"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ayusrjn/ensemble-customer-analyzer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ayusrjn%2Fensemble-customer-analyzer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ayusrjn%2Fensemble-customer-analyzer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ayusrjn%2Fensemble-customer-analyzer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ayusrjn%2Fensemble-customer-analyzer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ayusrjn","download_url":"https://codeload.github.com/ayusrjn/ensemble-customer-analyzer/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ayusrjn%2Fensemble-customer-analyzer/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30164530,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-06T04:43:31.446Z","status":"ssl_error","status_checked_at":"2026-03-06T04:40:30.133Z","response_time":250,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":["distillbert-model","ensemble","roberta-base","setfit-absa"],"created_at":"2026-03-06T06:00:03.129Z","updated_at":"2026-03-06T06:00:05.119Z","avatar_url":"https://github.com/ayusrjn.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RoBerta and DistillBert Based Advanced Abstract Based Sentiment Analysis App\n\n## Overview\nAn advanced sentiment analysis system trained on Flipkart product reviews, combining the power of RoBERTa and DistilBERT models in an ensemble approach. The system not only classifies sentiment but also extracts key aspects from negative reviews for better insights.\n\n## Application Screenshots\n\n![Main Dashboard](assets/dashboard.png)\n*Main application dashboard showing sentiment distribution*\n\n![Results Page](assets/results.png)\n*Detailed analysis results with sentiment breakdown*\n\n![Abstract Based Results](assets/absa.png)\n*Extracts the context of the reviews*\n\n![Confidence](assets/upload.png)\n*gives confidence of the model*\n\n## Features\n- **Ensemble Model Architecture**\n    - Fine-tuned RoBERTa\n    - Fine-tuned DistilBERT\n    - Enhanced accuracy through model combination\n\n- **Sentiment Analysis Capabilities**\n    - Positive/Negative classification\n    - Confidence scores\n    - Abstract extraction from negative reviews\n\n- **Review Analysis Features**\n    - Aspect-based sentiment extraction\n    - Key pain points identification\n    - Review summarization\n\n## Usage\n```python\n# Import required libraries\nfrom transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification\nfrom sentiment_analyzer import FlipkartAnalyzer\n\n# Load models from Hugging Face Hub\nroberta_model = AutoModelForSequenceClassification.from_pretrained(\"ayusrjn/RoBerta-finetuned-flipkar-review\")\nroberta_tokenizer = AutoTokenizer.from_pretrained(\"roberta-base\")\n\ndistilbert_model = AutoModelForSequenceClassification.from_pretrained(\"ayusrjn/distillBert-finetuned-on-flipkart-reviews\")\ndistilbert_tokenizer = AutoTokenizer.from_pretrained(\"distilbert-base-uncased\")\n\n```\n\n# Change the model path in the application \n  pages/1_Results.py\n  ```python\n  // line 66 to 71\n  results_df = predict_from_csv(\n                csv_path=temp_csv_path,\n                text_column='Comments',\n                roberta_path=roberta_model,\n                distil_path=distilbert,\n                num_labels=3)\n ```\n# Change absa model path \nabsa.py \n  ```python\n  model = AbsaModel.from_pretrained(\n    \"models\\setfit-absa-model-aspect\",\n    \"models\\setfit-absa-model-polarity\"\n)\n# Download the model from Hugging Face \"ayusrjn/setfit-absa/setfit-absa-model-aspect\" and \"ayusrjn/setfit-absa/setfit-absa-model-aspect\"\n\n ```\n\n## Example File\nexample.csv\n\n\n## Installation\n```bash\npip install -r requirements.txt\n```\n\n## Running\n```bash\nstreamlit run app1.py\n```\n\n\n## License\nMIT License\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fayusrjn%2Fensemble-customer-analyzer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fayusrjn%2Fensemble-customer-analyzer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fayusrjn%2Fensemble-customer-analyzer/lists"}