{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TP7QK7XDXVQBSWQT7XPH5WJHTS","short_pith_number":"pith:TP7QK7XD","schema_version":"1.0","canonical_sha256":"9bff057ee3bd60195a13fdde7ed9279caef0998582248a7548573956ae1b2ba4","source":{"kind":"arxiv","id":"2210.17495","version":2},"attestation_state":"computed","paper":{"title":"Automated Code Extraction from Discussion Board Text Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"James Folkestad, Marcia Moraes, Sadaf Ghaffari, Sina Mahdipour Saravani, Yanye Luther","submitted_at":"2022-10-31T17:20:32Z","abstract_excerpt":"This study introduces and investigates the capabilities of three different text mining approaches, namely Latent Semantic Analysis, Latent Dirichlet Analysis, and Clustering Word Vectors, for automating code extraction from a relatively small discussion board dataset. We compare the outputs of each algorithm with a previous dataset that was manually coded by two human raters. The results show that even with a relatively small dataset, automated approaches can be an asset to course instructors by extracting some of the discussion codes, which can be used in Epistemic Network Analysis."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.17495","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-31T17:20:32Z","cross_cats_sorted":[],"title_canon_sha256":"3b0381f6934d72a13cae1f8f72728c66105656e28535f9d956f900c3e86cc69e","abstract_canon_sha256":"af1f817627ca63aef89f7ffa44c5852388c8dbbdf95383d56a8f58ccdf48c328"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:30.415727Z","signature_b64":"pA6kKwx7FvgFfMi7rHnCN4hdi/6b2bf+feRxB7a1wBEMjtpxFn3lAP8EiWuJENFEc6inczIfP41u8nFfb6pmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bff057ee3bd60195a13fdde7ed9279caef0998582248a7548573956ae1b2ba4","last_reissued_at":"2026-07-05T06:02:30.414992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:30.414992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Code Extraction from Discussion Board Text Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"James Folkestad, Marcia Moraes, Sadaf Ghaffari, Sina Mahdipour Saravani, Yanye Luther","submitted_at":"2022-10-31T17:20:32Z","abstract_excerpt":"This study introduces and investigates the capabilities of three different text mining approaches, namely Latent Semantic Analysis, Latent Dirichlet Analysis, and Clustering Word Vectors, for automating code extraction from a relatively small discussion board dataset. We compare the outputs of each algorithm with a previous dataset that was manually coded by two human raters. The results show that even with a relatively small dataset, automated approaches can be an asset to course instructors by extracting some of the discussion codes, which can be used in Epistemic Network Analysis."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.17495","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.17495/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.17495","created_at":"2026-07-05T06:02:30.415064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.17495v2","created_at":"2026-07-05T06:02:30.415064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.17495","created_at":"2026-07-05T06:02:30.415064+00:00"},{"alias_kind":"pith_short_12","alias_value":"TP7QK7XDXVQB","created_at":"2026-07-05T06:02:30.415064+00:00"},{"alias_kind":"pith_short_16","alias_value":"TP7QK7XDXVQBSWQT","created_at":"2026-07-05T06:02:30.415064+00:00"},{"alias_kind":"pith_short_8","alias_value":"TP7QK7XD","created_at":"2026-07-05T06:02:30.415064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TP7QK7XDXVQBSWQT7XPH5WJHTS","json":"https://pith.science/pith/TP7QK7XDXVQBSWQT7XPH5WJHTS.json","graph_json":"https://pith.science/api/pith-number/TP7QK7XDXVQBSWQT7XPH5WJHTS/graph.json","events_json":"https://pith.science/api/pith-number/TP7QK7XDXVQBSWQT7XPH5WJHTS/events.json","paper":"https://pith.science/paper/TP7QK7XD"},"agent_actions":{"view_html":"https://pith.science/pith/TP7QK7XDXVQBSWQT7XPH5WJHTS","download_json":"https://pith.science/pith/TP7QK7XDXVQBSWQT7XPH5WJHTS.json","view_paper":"https://pith.science/paper/TP7QK7XD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.17495&json=true","fetch_graph":"https://pith.science/api/pith-number/TP7QK7XDXVQBSWQT7XPH5WJHTS/graph.json","fetch_events":"https://pith.science/api/pith-number/TP7QK7XDXVQBSWQT7XPH5WJHTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TP7QK7XDXVQBSWQT7XPH5WJHTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TP7QK7XDXVQBSWQT7XPH5WJHTS/action/storage_attestation","attest_author":"https://pith.science/pith/TP7QK7XDXVQBSWQT7XPH5WJHTS/action/author_attestation","sign_citation":"https://pith.science/pith/TP7QK7XDXVQBSWQT7XPH5WJHTS/action/citation_signature","submit_replication":"https://pith.science/pith/TP7QK7XDXVQBSWQT7XPH5WJHTS/action/replication_record"}},"created_at":"2026-07-05T06:02:30.415064+00:00","updated_at":"2026-07-05T06:02:30.415064+00:00"}