{"id":"W4386690757","doi":"10.18280/isi.280430","title":"Application of LSTM and GloVe Word Embedding for Hate Speech Detection in Indonesian Twitter Data","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Universitas Muhammadiyah Surakarta","keywords":"Indonesian; Computer science; Word (group theory); Speech recognition; Natural language processing; Word embedding; Artificial intelligence; Embedding; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007987879,0.000114797,0.0001539485,0.0004974374,0.0001214532,0.0001817694,0.0003743036,0.00009855038,7.760764e-7],"category_scores_gemma":[0.0001384571,0.0001199899,0.000024518,0.0009993153,0.00003997337,0.003356544,0.0001969631,0.00008234969,0.00002739776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001006954,"about_ca_system_score_gemma":0.00003034915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001660579,"about_ca_topic_score_gemma":0.00005776526,"domain_scores_codex":[0.9988792,0.00003301197,0.0004638395,0.0002096782,0.0001828966,0.0002313517],"domain_scores_gemma":[0.999059,0.00006287565,0.0002562787,0.0004672517,0.0001120082,0.00004262415],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003245879,0.000008664564,0.0009576915,0.0002687133,0.00001074085,7.762012e-7,0.002660919,0.0003611598,0.003886102,0.0005201071,0.00007086928,0.9912218],"study_design_scores_gemma":[0.0005957474,0.00008556912,0.0191571,0.0001071787,0.000007961958,0.00003087672,0.0006606509,0.9444826,0.02572937,0.007141163,0.001791526,0.0002102489],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3698111,0.000010663,0.6292049,0.00005061837,0.0001814757,0.0004251164,0.000008183924,0.0001463342,0.0001617087],"genre_scores_gemma":[0.9883262,0.0000199142,0.0113644,0.00003890636,0.00003704058,0.00008641792,0.0001038009,0.000007306223,0.00001600996],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9910116,"threshold_uncertainty_score":0.4893047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02253170171451098,"score_gpt":0.2671423331600427,"score_spread":0.2446106314455317,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}