{"record": {"aliases": ["nlp-sentiment-analysis-benchmark"], "artifacts": [{"id": "gh:anisha-das-kts/nlp-sentiment-analysis-benchmark", "kind": "repo", "url": "https://github.com/anisha-das-kts/nlp-sentiment-analysis-benchmark"}], "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "A reproducible NLP benchmarking project comparing three sentiment-analysis approaches on the NLTK Movie Reviews dataset, reporting predictive performance alongside training cost, latency, and error analysis."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://github.com/anisha-das-kts/nlp-sentiment-analysis-benchmark", "source": "claire_radar", "source_url": "https://github.com/anisha-das-kts/nlp-sentiment-analysis-benchmark", "title": "NLP Sentiment Analysis Benchmark"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:github:anisha-das-kts/nlp-sentiment-analysis-benchmark", "modality": null, "name": "NLP Sentiment Analysis Benchmark", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-candidate", "display_eligible": "false", "origin_record_id": "bm_nlp-sentiment-analysis-benchmark_f53e4e25", "origin_source": "github", "recognition_confidence": "0.4", "record_sha256": "f94dbd9a3efa5080a4678bc287e602532a8f77dec577ff628446d7149fae5382", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-09T01:08:06.842497Z", "source_url": "https://github.com/anisha-das-kts/nlp-sentiment-analysis-benchmark"}, "publisher": null, "released": "2026-09-06", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:github:anisha-das-kts/nlp-sentiment-analysis-benchmark", "source_url": "https://github.com/anisha-das-kts/nlp-sentiment-analysis-benchmark"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-github-anisha-das-kts-nlp-sentiment-analysis-benchmark", "source": "claire_radar", "source_benchmark_id": "github:anisha-das-kts/nlp-sentiment-analysis-benchmark", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["nlp-sentiment-analysis-benchmark"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/anisha-das-kts/nlp-sentiment-analysis-benchmark", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": null, "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"state": "not_applicable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The educational sentiment comparison project has limited novelty and no standalone public comparison path, so early interest is expected to be minimal.", "score": 8}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-09T01:08:06.842497Z", "inputHash": "39ebb36a61c300542ac0d29d991c1ca7fc3019a7866beaf612741d92795078d8", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "# NLP Sentiment Analysis Benchmark A reproducible NLP benchmarking project comparing three sentiment-analysis approaches on the NLTK Movie Reviews dataset:", "canonicalNameSource": "official_readme", "decisionReason": "The repository describes a reproducible comparison of three fixed models on a public dataset and does not define a benchmark allowing other teams to submit models or reuse a standardized evaluation protocol; it is a single-paper viewpoint probe.", "evaluationEvidence": {"reuse": "python scripts/evaluate.py", "scoring": "Accuracy, Macro F1, Positive-Class F1, classification reports, and confusion matrices", "task": "The project uses the **NLTK Movie Reviews** corpus. The dataset is downloaded programmatically through NLTK, so the corpus itself is not committed to the repository."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-09T01:08:06.842497Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "A reproducible NLP benchmarking project comparing three sentiment-analysis approaches on the NLTK Movie Reviews dataset, reporting predictive performance alongside training cost, latency, and error analysis.", "discoverySources": [{"id": "github:anisha-das-kts/nlp-sentiment-analysis-benchmark", "type": "github", "url": "https://github.com/anisha-das-kts/nlp-sentiment-analysis-benchmark"}], "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["discovered via github", "benchmark term in abstract", "evaluation protocol evidence", "no explicit benchmark release evidence"], "snippet": "nlp-sentiment-analysis-benchmark # NLP Sentiment Analysis Benchmark A reproducible NLP benchmarking project comparing three approaches to binary sentiment analysis on the **NLTK Movie Reviews dataset**: * **TF-IDF + Logistic Regression** — traditional supervised machine learning * **PyTorch LSTM** — deep learning with learned word embeddings * **VADER** — lexicon and rule-based sentiment analysis The project evaluates predictive performance together with training cost, inference latency, error b"}, "familyId": "bmf_a1ce21e14739", "firstSeenAt": "2026-09-07", "heat": null, "id": "bm_nlp-sentiment-analysis-benchmark_f53e4e25", "indexedAt": "2026-09-07T06:22:04.880155Z", "industrySectors": [], "links": {"code": "https://github.com/anisha-das-kts/nlp-sentiment-analysis-benchmark"}, "metrics": [], "motivation": "nlp-sentiment-analysis-benchmark # NLP Sentiment Analysis Benchmark A reproducible NLP benchmarking project comparing three approaches to binary sentiment analysis on the **NLTK Movie Reviews dataset**: * **TF-IDF + Logistic Regression** — traditional supervised machine learning * **PyTorch LSTM** — deep learning with learned word embeddings * **VADER** — lexicon and rule-based sentiment analysis The project evaluat…", "name": "NLP Sentiment Analysis Benchmark", "oneLine": "A reproducible NLP benchmarking project comparing three sentiment-analysis approaches on the NLTK Movie Reviews dataset, reporting predictive performance alongside training cost, latency, and error analysis.", "paperTitle": "nlp-sentiment-analysis-benchmark", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://github.com/anisha-das-kts/nlp-sentiment-analysis-benchmark", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-07T06:22:04.880155Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 203, "score": 23}, "method": "attention-ranking-v13", "rank": 203, "score": 23}, "90d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 467, "score": 23}, "method": "attention-ranking-v13", "rank": 467, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-09-06", "source": {"authors": ["anisha-das-kts"], "categories": [], "id": "github:anisha-das-kts/nlp-sentiment-analysis-benchmark", "publicSignals": {"githubStars": 0}, "title": "nlp-sentiment-analysis-benchmark", "type": "github", "url": "https://github.com/anisha-das-kts/nlp-sentiment-analysis-benchmark"}, "sourceUpdatedAt": "2026-09-06T17:02:09Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "The project provides a local comparison of traditional ML, deep learning, and lexicon-based sentiment analysis, but it is a single-model comparison study rather than a formal benchmark with a reusable evaluation protocol."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
