{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XOEGGRESXDKPINOH4LRDSKKZDU","short_pith_number":"pith:XOEGGRES","schema_version":"1.0","canonical_sha256":"bb88634492b8d4f435c7e2e23929591d13d1c76c69c366d73881b69ba71f371c","source":{"kind":"arxiv","id":"2011.01612","version":2},"attestation_state":"computed","paper":{"title":"XED: A Multilingual Dataset for Sentiment Analysis and Emotion Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Emily \\\"Ohman, J\\\"org Tiedemann, Kaisla Kajava, Marc P\\`amies","submitted_at":"2020-11-03T10:43:22Z","abstract_excerpt":"We introduce XED, a multilingual fine-grained emotion dataset. The dataset consists of human-annotated Finnish (25k) and English sentences (30k), as well as projected annotations for 30 additional languages, providing new resources for many low-resource languages. We use Plutchik's core emotions to annotate the dataset with the addition of neutral to create a multilabel multiclass dataset. The dataset is carefully evaluated using language-specific BERT models and SVMs to show that XED performs on par with other similar datasets and is therefore a useful tool for sentiment analysis and emotion "},"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":"2011.01612","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-03T10:43:22Z","cross_cats_sorted":[],"title_canon_sha256":"8f8b2aaac970b189a862f9729a68fada5e5a9fb4b77c81b6a296c7795d722c91","abstract_canon_sha256":"d3207368fc58eae36eb4bf290dbfdae97d56ca20c22bae9e8ec1a20bebcbd833"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:39.403148Z","signature_b64":"MXRHQJRtSEBCo7rQiyfc1u8TfbnvIZOjH1h+0/NJyfFnXoT/zV90XPQBarnB0iEPDzpWzqMMKb76agHx23oxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb88634492b8d4f435c7e2e23929591d13d1c76c69c366d73881b69ba71f371c","last_reissued_at":"2026-07-05T01:49:39.402712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:39.402712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XED: A Multilingual Dataset for Sentiment Analysis and Emotion Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Emily \\\"Ohman, J\\\"org Tiedemann, Kaisla Kajava, Marc P\\`amies","submitted_at":"2020-11-03T10:43:22Z","abstract_excerpt":"We introduce XED, a multilingual fine-grained emotion dataset. The dataset consists of human-annotated Finnish (25k) and English sentences (30k), as well as projected annotations for 30 additional languages, providing new resources for many low-resource languages. We use Plutchik's core emotions to annotate the dataset with the addition of neutral to create a multilabel multiclass dataset. The dataset is carefully evaluated using language-specific BERT models and SVMs to show that XED performs on par with other similar datasets and is therefore a useful tool for sentiment analysis and emotion "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01612","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/2011.01612/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":"2011.01612","created_at":"2026-07-05T01:49:39.402775+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.01612v2","created_at":"2026-07-05T01:49:39.402775+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01612","created_at":"2026-07-05T01:49:39.402775+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOEGGRESXDKP","created_at":"2026-07-05T01:49:39.402775+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOEGGRESXDKPINOH","created_at":"2026-07-05T01:49:39.402775+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOEGGRES","created_at":"2026-07-05T01:49:39.402775+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06803","citing_title":"Emotion Recognition and Generation: A Comprehensive Review of Face, Speech, and Text Modalities","ref_index":183,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOEGGRESXDKPINOH4LRDSKKZDU","json":"https://pith.science/pith/XOEGGRESXDKPINOH4LRDSKKZDU.json","graph_json":"https://pith.science/api/pith-number/XOEGGRESXDKPINOH4LRDSKKZDU/graph.json","events_json":"https://pith.science/api/pith-number/XOEGGRESXDKPINOH4LRDSKKZDU/events.json","paper":"https://pith.science/paper/XOEGGRES"},"agent_actions":{"view_html":"https://pith.science/pith/XOEGGRESXDKPINOH4LRDSKKZDU","download_json":"https://pith.science/pith/XOEGGRESXDKPINOH4LRDSKKZDU.json","view_paper":"https://pith.science/paper/XOEGGRES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.01612&json=true","fetch_graph":"https://pith.science/api/pith-number/XOEGGRESXDKPINOH4LRDSKKZDU/graph.json","fetch_events":"https://pith.science/api/pith-number/XOEGGRESXDKPINOH4LRDSKKZDU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOEGGRESXDKPINOH4LRDSKKZDU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOEGGRESXDKPINOH4LRDSKKZDU/action/storage_attestation","attest_author":"https://pith.science/pith/XOEGGRESXDKPINOH4LRDSKKZDU/action/author_attestation","sign_citation":"https://pith.science/pith/XOEGGRESXDKPINOH4LRDSKKZDU/action/citation_signature","submit_replication":"https://pith.science/pith/XOEGGRESXDKPINOH4LRDSKKZDU/action/replication_record"}},"created_at":"2026-07-05T01:49:39.402775+00:00","updated_at":"2026-07-05T01:49:39.402775+00:00"}