{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4GUC4WACOXNCNEHV4T7IMDQKLC","short_pith_number":"pith:4GUC4WAC","schema_version":"1.0","canonical_sha256":"e1a82e580275da2690f5e4fe860e0a58b1554b23021076265f47d83f8bdc2a43","source":{"kind":"arxiv","id":"1705.09995","version":1},"attestation_state":"computed","paper":{"title":"Subject Specific Stream Classification Preprocessing Algorithm for Twitter Data Stream","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chamilka Wijeratne, Danaja Maldeniya, Nisansa de Silva","submitted_at":"2017-05-28T22:16:35Z","abstract_excerpt":"Micro-blogging service Twitter is a lucrative source for data mining applications on global sentiment. But due to the omnifariousness of the subjects mentioned in each data item; it is inefficient to run a data mining algorithm on the raw data. This paper discusses an algorithm to accurately classify the entire stream in to a given number of mutually exclusive collectively exhaustive streams upon each of which the data mining algorithm can be run separately yielding more relevant results with a high efficiency."},"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":"1705.09995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-28T22:16:35Z","cross_cats_sorted":[],"title_canon_sha256":"cbe855e2886daeaded2ea70c39017ab3fe7acab053a0e279e6c8f7e1f3806a20","abstract_canon_sha256":"6ff399067957d138a10972a4e762577a9c2ae00f9c44ebc4f2c0b3215e6055f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:33.992473Z","signature_b64":"1+IeFNjNnWuDWGmT+hUwnpp9B9Ca+AEUAp4wknxvtX3f7sGq/AGFWeYvZET4hPK3B6IfhcylfGJh168b7qNZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1a82e580275da2690f5e4fe860e0a58b1554b23021076265f47d83f8bdc2a43","last_reissued_at":"2026-05-18T00:43:33.992026Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:33.992026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Subject Specific Stream Classification Preprocessing Algorithm for Twitter Data Stream","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chamilka Wijeratne, Danaja Maldeniya, Nisansa de Silva","submitted_at":"2017-05-28T22:16:35Z","abstract_excerpt":"Micro-blogging service Twitter is a lucrative source for data mining applications on global sentiment. But due to the omnifariousness of the subjects mentioned in each data item; it is inefficient to run a data mining algorithm on the raw data. This paper discusses an algorithm to accurately classify the entire stream in to a given number of mutually exclusive collectively exhaustive streams upon each of which the data mining algorithm can be run separately yielding more relevant results with a high efficiency."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.09995","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1705.09995","created_at":"2026-05-18T00:43:33.992093+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.09995v1","created_at":"2026-05-18T00:43:33.992093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.09995","created_at":"2026-05-18T00:43:33.992093+00:00"},{"alias_kind":"pith_short_12","alias_value":"4GUC4WACOXNC","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"4GUC4WACOXNCNEHV","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"4GUC4WAC","created_at":"2026-05-18T12:30:58.224056+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/4GUC4WACOXNCNEHV4T7IMDQKLC","json":"https://pith.science/pith/4GUC4WACOXNCNEHV4T7IMDQKLC.json","graph_json":"https://pith.science/api/pith-number/4GUC4WACOXNCNEHV4T7IMDQKLC/graph.json","events_json":"https://pith.science/api/pith-number/4GUC4WACOXNCNEHV4T7IMDQKLC/events.json","paper":"https://pith.science/paper/4GUC4WAC"},"agent_actions":{"view_html":"https://pith.science/pith/4GUC4WACOXNCNEHV4T7IMDQKLC","download_json":"https://pith.science/pith/4GUC4WACOXNCNEHV4T7IMDQKLC.json","view_paper":"https://pith.science/paper/4GUC4WAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.09995&json=true","fetch_graph":"https://pith.science/api/pith-number/4GUC4WACOXNCNEHV4T7IMDQKLC/graph.json","fetch_events":"https://pith.science/api/pith-number/4GUC4WACOXNCNEHV4T7IMDQKLC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4GUC4WACOXNCNEHV4T7IMDQKLC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4GUC4WACOXNCNEHV4T7IMDQKLC/action/storage_attestation","attest_author":"https://pith.science/pith/4GUC4WACOXNCNEHV4T7IMDQKLC/action/author_attestation","sign_citation":"https://pith.science/pith/4GUC4WACOXNCNEHV4T7IMDQKLC/action/citation_signature","submit_replication":"https://pith.science/pith/4GUC4WACOXNCNEHV4T7IMDQKLC/action/replication_record"}},"created_at":"2026-05-18T00:43:33.992093+00:00","updated_at":"2026-05-18T00:43:33.992093+00:00"}