{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001771207,0.0002242403,0.0004022325,0.0004991983,0.0002648577,0.0007439425,0.002074893,0.00006383018,0.000002005266],"category_scores_gemma":[0.0001350915,0.0002248651,0.0001431373,0.002574308,0.00008361554,0.001537098,0.0006730661,0.0001059441,0.000001904663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008053661,"about_ca_system_score_gemma":0.00007903951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002968901,"about_ca_topic_score_gemma":0.0008644304,"domain_scores_codex":[0.9976015,0.0003774753,0.0003354026,0.0007762514,0.0005271512,0.0003821912],"domain_scores_gemma":[0.9974292,0.0006019791,0.0002228645,0.001362017,0.0002721071,0.0001118275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001468068,0.0003819461,0.9391546,0.00005143945,0.001195869,0.00001435914,0.0004310055,0.03766421,0.007838571,0.0002704888,0.002253687,0.01059701],"study_design_scores_gemma":[0.0006733334,0.00008035827,0.2721266,0.00001798125,0.000514377,3.81606e-7,0.00001934988,0.695314,0.0273793,0.003350107,0.00007318021,0.0004510267],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4713058,0.00002042386,0.5280438,0.00007485916,0.00009759415,0.000196788,0.00002226878,0.0002371032,0.000001349204],"genre_scores_gemma":[0.9593405,0.000007099624,0.04004952,0.0002735624,0.0001407424,0.00004934505,0.00005001623,0.00002812168,0.00006106122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.667028,"threshold_uncertainty_score":0.9169731,"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."}}