{"id":"W4385834249","doi":"10.1109/access.2023.3305260","title":"Summarizing Students’ Free Responses for an Introductory Algebra-Based Physics Course Survey Using Cluster and Sentiment Analysis","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"University of Toronto","keywords":"Sentiment analysis; Likert scale; Computer science; Valence (chemistry); Set (abstract data type); Cluster grouping; Mathematics education; Macro; Natural language processing; Text messaging; Artificial intelligence; Information retrieval; Psychology; Statistics; World Wide Web; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003285738,0.0006883158,0.0006211601,0.004381629,0.0004565141,0.000871198,0.000351636,0.0004205071,0.002551998],"category_scores_gemma":[0.01826823,0.0001375789,0.0004471489,0.003417131,0.0002279781,0.0005728006,0.0008442489,0.0004614985,0.001398475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004284988,"about_ca_system_score_gemma":0.000406063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001096047,"about_ca_topic_score_gemma":0.002470159,"domain_scores_codex":[0.9961296,0.001525052,0.000437862,0.0004783476,0.001225247,0.0002039209],"domain_scores_gemma":[0.9780666,0.01121288,0.002481206,0.001701122,0.005919755,0.000618384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001332359,0.001168878,0.3338985,0.00141862,0.0004878715,0.0002321751,0.01071484,0.005641871,0.05582454,0.001054026,0.04260071,0.5456256],"study_design_scores_gemma":[0.00008253019,0.001299516,0.8830705,0.0001249657,0.0001856384,0.0001715981,0.01120355,0.05176457,0.0260791,0.002155036,0.02358863,0.0002743379],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9418337,0.0001038659,0.04132191,0.0002701088,0.0001123848,0.001007733,0.0113198,0.001254019,0.002776392],"genre_scores_gemma":[0.9114134,0.0001202407,0.06500967,0.0001552355,0.0001486341,0.002439778,0.01759228,0.0002120712,0.002908618],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004381629,"threshold_uncertainty_score":0.01737684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.102502715933714,"score_gpt":0.4265102288346814,"score_spread":0.3240075129009674,"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."}}