This thesis investigates the possibility of automating the classification of post-feedback mathematical reasoning styles, Creative Mathematical Reasoning (CMR) and Algorithmic Reasoning (AR), using prompt-based classification with a Large Language Model (LLM). The study, conducted in collaboration with the Department of Science and Mathematics Education of Umeå University, aims to enhance the efficiency of pedagogical research by reducing the manual labor involved in classifying student responses. The thesis utilizes a dataset of 40 expert-labeled student mathematical solutions, incorporating feedback interactions to assess shifts in reasoning post-feedback. Various prompting methods, including definitions-only and examples-inclusive prompts, were systematically tested to determine their effectiveness in classifying reasoning styles. The classification performance was measured using accuracy, F1-score, and Cohen’s kappa. Results indicate that definitionbased prompts performed robustly, achieving moderate to strong inter-rater agreement. The study also explored the impact of output formats and found that allowing the LLM to classify uncertain cases as indeterminate could potentially automate about 25% of the classification tasks without compromising performance. This thesis underscores the potential of LLMs in automating complex cognitive task classifications in educational research, suggesting further exploration into optimal prompting strategies and reliability enhancements for practical applications. / Denna uppsats undersöker möjligheten att automatisera klassificeringen av matematiska resonemangstyper efter feedback, Kreativt Matematiskt Resonemang (CMR) och Algoritmiskt Resonemang (AR), med hjälp av promptbaserad klassificering med en stor språkmodell (LLM). Studien, som genomfördes i samarbete med Institutionen för naturvetenskapernas och matematikens didaktik vid Umeå universitet, syftar till att öka effektiviteten i pedagogisk forskning genom att minska det manuella arbetet som krävs för att klassificera studenters matematiska resonemang. Uppsatsen använder ett dataset med 40 matematiska lösningar från studenter, klassificerade av experter. Dessa lösningar inkluderar feedback-interaktioner för att bedöma förändringar i resonemang efter feedback. Olika promptmetoder, innehållandes enbart definitioner och exempel-inkluderande promptar, testades systematiskt för att avgöra deras effektivitet vid klassificering av resonemangsstilar. Klassificeringsprestandan mättes med hjälp av accuracy, F1-score och Cohen’s kappa. Resultaten visar att promptar baserade på definitioner hade en robust prestanda och uppnådde måttlig till stark överensstämmelse mellan bedömare. Studien undersökte också påverkan av utdataformat och fann att genom att tillåta LLM att klassificera osäkra fall som obestämdbarkunde cirka 25% av klassificeringsuppgifterna automatiseras utan att kompromissa med prestandan. Denna avhandling framhäver potentialen hos LLMs att automatisera komplexa kognitiva uppgiftsklassificeringar inom utbildningsforskning och föreslår vidare studier av optimala promptstrategier och tillförlitlighetsförbättringar för praktiska tillämpningar.

The purpose of this research study was to provide training for peer tutors to use simultaneous prompting to increase the percentage of correct responses of sight words by students with moderate to severe disabilities. The study included four students with moderate to severe disabilities in an elementary school setting. A multiple probe (days) design across behaviors replicated across students was used to evaluate the effectiveness of the simultaneous prompting procedure used by peer tutors to teach students with moderate to severe disabilities in the general education setting. The results indicated the peers were able to reliably implement the procedures, but a functional relation was demonstrated with only one participant.

The purpose of this study was to investigate the effects of explicit instruction combined with video prompting to teach text comprehension skills to students with autism spectrum disorder. Participants included 4 elementary school students with autism. A multiple probe across participants design was used to evaluate the intervention’s effectiveness. Results indicated that the intervention was successful for all participants. All participants mastered the comprehension skills; however, data were highly variable during the acquisition phase. Implications for researchers and practitioners are discussed.

The purpose of the study was to provide training to peer tutors to teach students with mild and moderate disabilities sales tax computation using a simultaneous prompting procedure with fidelity. Non-target information presented during training sessions and generalization to natural environment settings was assessed. A multiple probe (days) across participants design was used to evaluate the effectiveness of the intervention on the dependent variables. The results showed peer tutors could use the simultaneous prompting procedure with fidelity to teach sales tax computation and students with disabilities could acquire sales tax computation. The students acquired the non-target information presented and generalization occurred in a natural setting.

In the present experiment, a remote control tactile prompting device (RCT) was utilized to prompt a child with autism to recruit teacher models and play suggestions. A multiple baseline and reversal was used to assess the effects of the RCT across three play contexts. The results showed increases in the number of requests for models and suggestions as well as increases in the duration of interactive play between the child and therapist, the number of contextual statements emitted by the child, and the topography and contexts of the play behaviors emitted by the child. Findings are discussed in terms of the effectiveness and generality of the RCT and the issue of teaching a child to recruit versus teaching a child activity-specific behaviors.

The general purpose of the current study was to evaluate the effects of minimally intrusive prompting procedures and preferred stimuli on protodeclarative joint attention initiations in children diagnosed with autism spectrum disorder (ASD). Two boys and one girl diagnosed with ASD participated. The experimenter provided attention and social interaction following protodeclarative initiations throughout all phases of the study. During intervention, a model prompt was delivered every 30 s if the participant failed to initiate a bid for joint attention. Results for the first participant show that a model prompt was sufficient to increase the rate of protodeclarative initiations across stimulus sets. Generalization was seen across sets, but not across environments. Subsequently, the model prompt was sufficient to increase the rate of protodeclarative initiations across sets in a second setting (classroom). Results for the second participant are inconclusive. Data collected during the initial baseline condition show that she engaged in an incompatible verbal response across sets. When pictorial stimuli depicting highinterest items and activities were introduced, the rate of protodeclarative initiations increased over time. We then returned to original baseline condition and saw an initial decrease, followed by a steady increase in the rate of protodeclarative initiations. The third participant withdrew prematurely due to medical reasons. The findings of the current study show that minimally intrusive prompts and natural consequences may be sufficient to establish protodeclarative initiations in children. However, this finding may be limited to only those children for whom social interactions already function as reinforcers.

One useful strategy to support students with intellectual and developmental disability (IDD) to promote appropriate behaviors across environments and gain the social skills is using social stories. In addition, experts have recognized iPads and apps were associated with less challenging behavior and more academic engagement over traditional materials (Lee, Lang, Davenport, Moore, Rispoli, Meer, & Chung, 2013). The focus this study was to examine the effectiveness of an intervention package featuring social stories delivered via an iPad and simultaneous prompting on frequency of targeted challenging behavior and comprehension of the social story of a student with IDD. A single-subject multiple probe across behaviors (Kennedy, 2005) design was used to investigate the effectiveness of this intervention on the student's ability to correctly match pictures to steps in social stories as well as the targeted challenging behaviors. The results, future research, and the limitations of the study are discussed.

Peer mediated interventions have been effective in teaching academic and social skills to students with disabilities. The present study assesses the effectiveness of students with autism spectrum disorder serving as the tutor and tutee. Four peer mediators and four students with autism spectrum disorder used technology and the simultaneous prompting procedure to teach acquisition of social studies vocabulary. Results indicate that both students with and without autism spectrum disorder effectively delivered instruction using technology and all students learned a portion of the vocabulary taught by a same-aged peer.

Research shows that young children, typically developing with no developmental delays, hearing impairments or visual impairments, can acquire sign language to communicate their wants or needs prior to their ability to communicate through spoken language. However, much of the research reviewed focused on whether it was normative for young children to use signs or symbolic gestures to represent objects, make requests, or to express other wants or needs. In addition, many of the studies reviewed lacked scientific rigor and were primarily anecdotal in that much of the data relied on parent reports of his/her child's production of signs or symbolic gestures. The present study expanded upon the procedures of Thompson, McKerchar, and Dancho (2004) by teaching more complex signing repertoires using different training procedures. This study examined the acquisition of functional sign language by typically developing infants, ranging in age from 10 months to 14 months, using a training program which consisted of three components. The three components of intervention included a 30 minute group class once per week, an intensive or "booster" 1:1 session twice per week, and parent led training in the participant's home environment. During intervention a variety of concept items such as toys, pictures, books, and real objects were presented to represent the signs were utilized. A multiple baseline design across pairs of behaviors was employed to assess experimental changes in signing repertoires during the intervention conditions. All participants demonstrated zero rates of signing during baseline and showed an increase in their signing repertoires during intervention phases.

The intraverbal is argued to be the most socially significant verbal operant and yet it is the least studied. Heal and Hanley (2011) suggest that different teaching strategies will lead to different rates of acquisition and child-preference with the tacting operant. This study continued this research into the realm of intraverbals, with focus on whether the embedded teaching strategy could be punishing on play or engaging in learning opportunities. The teaching strategies of discovery teaching, embedded prompting, and direct teaching were compared to see which strategy correlated with higher rates of acquisition and higher child preference. The study utilized a multi-element design by rapidly alternating teaching strategies while evaluating rate of acquisition and number of learning opportunities within the teaching strategies. Child preference was also demonstrated through card selection of associated teaching strategies in a concurrent chains agreement design. The teaching strategies differed in the amount of teacher directedness and taught intraverbal "Wh" questions. It was found through this study that embedded prompting did not punish play or the engagement in learning opportunities. The three participants preferred the three strategies differently and all participants were responding correctly the highest percentage of the time during the direct teaching contingencies by the end of the teaching sessions.