{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/190601830","title":"ArSentD-LEV: A Multi-Topic Corpus for Target-based Sentiment Analysis in Arabic Levantine Tweets","arxiv_id":"1906.01830","date":"2019-05-25","proceeding":null,"authors":["Ramy Baly","Alaa Khaddaj","Hazem Hajj","Wassim El-Hajj","Khaled Bashir Shaban"],"abstract":"Sentiment analysis is a highly subjective and challenging task. Its complexity further increases when applied to the Arabic language, mainly because of the large variety of dialects that are unstandardized and widely used in the Web, especially in social media. While many datasets have been released to train sentiment classifiers in Arabic, most of these datasets contain shallow annotation, only marking the sentiment of the text unit, as a word, a sentence or a document. In this paper, we present the Arabic Sentiment Twitter Dataset for the Levantine dialect (ArSenTD-LEV). Based on findings from analyzing tweets from the Levant region, we created a dataset of 4,000 tweets with the following annotations: the overall sentiment of the tweet, the target to which the sentiment was expressed, how the sentiment was expressed, and the topic of the tweet. Results confirm the importance of these annotations at improving the performance of a baseline sentiment classifier. They also confirm the gap of training in a certain domain, and testing in another domain.","url_abs":"https://arxiv.org/abs/1906.01830v1","url_pdf":"https://arxiv.org/pdf/1906.01830v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"190601830","repo_url":"https://github.com/CAMeL-Lab/CAMeLBERT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"190601830","repo_url":"https://github.com/alazraq/arabic-nlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[],"datasets_introduced":[{"slug":"arsentd-lev","name":"ArSentD-LEV","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.01830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.01830"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alazraq/arabic-nlp","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CAMeL-Lab/CAMeLBERT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"listed":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"9d577332fad44955","entry":"convert_examples_to_features","repo":"CAMeL-Lab/CAMeLBERT","repo_kind":"listed","path":"token-classification/utils.py","file_url":"https://github.com/CAMeL-Lab/CAMeLBERT/blob/HEAD/token-classification/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9d577332fad44955"}},{"code_sha256_prefix":"2381a5e005f32b13","entry":"get_labels","repo":"CAMeL-Lab/CAMeLBERT","repo_kind":"listed","path":"token-classification/utils.py","file_url":"https://github.com/CAMeL-Lab/CAMeLBERT/blob/HEAD/token-classification/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2381a5e005f32b13"}},{"code_sha256_prefix":"85b7c89f116679d9","entry":"read_data","repo":"CAMeL-Lab/CAMeLBERT","repo_kind":"listed","path":"text-classification/utils/vote_did.py","file_url":"https://github.com/CAMeL-Lab/CAMeLBERT/blob/HEAD/text-classification/utils/vote_did.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85b7c89f116679d9"}},{"code_sha256_prefix":"2b45eda8392df729","entry":"read_examples_from_file","repo":"CAMeL-Lab/CAMeLBERT","repo_kind":"listed","path":"token-classification/utils.py","file_url":"https://github.com/CAMeL-Lab/CAMeLBERT/blob/HEAD/token-classification/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b45eda8392df729"}},{"code_sha256_prefix":"8d8630faa01735cf","entry":"user_preds","repo":"CAMeL-Lab/CAMeLBERT","repo_kind":"listed","path":"text-classification/utils/vote_did.py","file_url":"https://github.com/CAMeL-Lab/CAMeLBERT/blob/HEAD/text-classification/utils/vote_did.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d8630faa01735cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}