【正文】 ummary].” Discourse Marker Relations y e a hy e sy e pO h y e a hT h a t 39。 Graesser, 2022) Four conditions 1. Human tutors 2. Why/Atlas 3. Why/AutoTutor 4. Read control 86 College Students Measures in Spring Evaluation ? Multiple Choice Test ? Pretest and posttest (40 multiple choice questions in each) ? Essays graded by 6 physics experts ? 4 pretest and 4 posttest essays ? Expectations versus misconceptions ? Wholistic grades ? Generic principles and misconceptions (finegrained) ? Learner perceptions ? Time on Tasks Effect Sizes on Learning Gains (pretest to posttest, no differences among tutoring conditions) 0 0 . 2 5 0 . 5 0 . 7 5 1 1 . 2 5 1 . 5Exp er t Gr ad esM i sco n cep ti o nr em o valExp ectati o n sl en i en tExp ectati o n sstr i n g en tM u l ti p l e C h o i ceEffe c t s i z eFall 2022 Evaluations Conceptual Physics (Graesser, Moreno, et al., 2022) Three tutoring conditions 1. Why/AutoTutor 2. Read textbook control 3. Read nothing 63 subjects Multiple Choice Scores 0 . 40 . 50 . 60 . 70 . 8W h y / A u t o T u t o r R e a d T e x t b o o k R e a d n o t h i n gMultiple Choice Test ScorePr e te s t Po s tte s t A d j u s te d p o s tte s t20223 Evaluations Computer Literacy (Graesser, Hu, et al., 2022) 2 Tutoring Conditions 1. AutoTutor 2. Read nothing 4 Media Conditions 1. Print 2. Speech 3. Speech+Head 4. Speech+Head+Print 96 subjects Deep Reasoning Questions 0 . 20 . 30 . 40 . 50 . 6W h y / A u t o T u t o r R e a d n o t h i n gMultiple Choice Test ScorePr i n t Sp e e c h H e a d +S H e a d +S+PLATENT SEMANTIC ANALYSIS Signal Detection Analyses 0 . 00 . 10 . 20 . 30 . 40 . 50 . 60 . 70 . 80 . 3 0 0 . 4 0 0 . 5 0 0 . 6 0 0 . 6 5L SA T h r e s h o l dH i t R a teF a l s e A l a r m R a ted 39。 sr i g h te x a c t l yI k n o wa p p a r e n t l yO h t h a t 39。AutoTutor: An Intelligent Tutoring System with Mixed Initiative Dialog Art Graesser University of Memphis Department of Psychology amp。 sf i n ea n dm h mr i g h ts u r eu n h u n hs i n c eb a s i c a l l yh e l lt h a t 39。 s c o r eRecall, Precision, and Fmeasure 0 . 00 . 10 . 20 . 30 . 40 . 50 . 60 . 70 . 80 . 90 . 3 0 0 . 4 0 0 . 5 0 0 . 6 0 0 . 6 5L SA T h r e s h o l dR e c a l lPr e c i s i o nF m e a s u r eWhat Expectations are LSAworthy? Compute correlation between: (a) Experts’ ratings of whether essay answers have expectation E (b) Maximum LSA cosine between E and all possible binations of sentences in essay A high correlation means the expectation is LSAworthy Expectations and Correlations (expert ratings, LSA) ? After the release, the only force on the balls is the force of the moon’s gravity (r = .71) ? A larger object will experience a smaller acceleration for the same force (r = .12) ? Force equals mass times acceleration (r = .67) ? The boxes are in free fall (r = .21) OTHER EMPIRICAL EVALUATIONS Assessment of Dialogue Management Bystander Turing test Participants rate whether particular dialog moves in conversations were generated by AutoTutor or by skilled human tutors. ♀ Bystander says Computer said it Bystander says Human said it Reality: Computer said it Hit .51 Miss .49 Reality: Human said it False alarm .53 CR .47 ASL Model 501 Eye Tracker QUESTION 4%