Explainable Collaborative Problem Solving Diagnosis with BERT using SHAP and its Implications for Teacher Adoption

• URL: http://arxiv.org/abs/2507.14584v1
• Date: Sat, 19 Jul 2025 11:57:24 GMT
• Title: Explainable Collaborative Problem Solving Diagnosis with BERT using SHAP and its Implications for Teacher Adoption
• Authors: Kester Wong, Sahan Bulathwela, Mutlu Cukurova,
• Abstract summary: This study examines how different tokenised words in transcription data contributed to a BERT model's classification of CPS processes.<n>The findings suggest that well-performing classifications did not equate to a reasonable explanation for the classification decisions.<n>The analysis also identified a spurious word, which contributed positively to the classification but was not semantically meaningful to the class.
• Score: 5.1126582076480505
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The use of Bidirectional Encoder Representations from Transformers (BERT) model and its variants for classifying collaborative problem solving (CPS) has been extensively explored within the AI in Education community. However, limited attention has been given to understanding how individual tokenised words in the dataset contribute to the model's classification decisions. Enhancing the explainability of BERT-based CPS diagnostics is essential to better inform end users such as teachers, thereby fostering greater trust and facilitating wider adoption in education. This study undertook a preliminary step towards model transparency and explainability by using SHapley Additive exPlanations (SHAP) to examine how different tokenised words in transcription data contributed to a BERT model's classification of CPS processes. The findings suggested that well-performing classifications did not necessarily equate to a reasonable explanation for the classification decisions. Particular tokenised words were used frequently to affect classifications. The analysis also identified a spurious word, which contributed positively to the classification but was not semantically meaningful to the class. While such model transparency is unlikely to be useful to an end user to improve their practice, it can help them not to overrely on LLM diagnostics and ignore their human expertise. We conclude the workshop paper by noting that the extent to which the model appropriately uses the tokens for its classification is associated with the number of classes involved. It calls for an investigation into the exploration of ensemble model architectures and the involvement of human-AI complementarity for CPS diagnosis, since considerable human reasoning is still required for fine-grained discrimination of CPS subskills.

Related papers

• Exploring Human-AI Complementarity in CPS Diagnosis Using Unimodal and Multimodal BERT Models [5.1126582076480505]
  This paper extends previous research by highlighting that the AudiBERT model improved the classification of classes that were sparse in the dataset.<n>Similar significant class-wise improvements over the BERT model were not observed for classifications in the affective dimension.<n>A correlation analysis highlighted that larger training data was significantly associated with higher recall performance for both the AudiBERT and BERT models.
  arXiv  Detail & Related papers  (2025-07-19T11:47:08Z)
• Rethinking the Potential of Multimodality in Collaborative Problem Solving Diagnosis with Large Language Models [0.562479170374811]
  multimodal data and advanced models are argued to have the potential to detect complex CPS behaviours.<n>We investigated the potential of multimodal data to improve model performance in diagnosing 78 secondary school students' CPS subskills and indicators.
  arXiv  Detail & Related papers  (2025-04-21T13:25:55Z)
• Probing Network Decisions: Capturing Uncertainties and Unveiling Vulnerabilities Without Label Information [19.50321703079894]
  We present a novel framework to uncover the weakness of the classifier via counterfactual examples.<n>We test the performance of our prober's misclassification detection and verify its effectiveness on the image classification benchmark datasets.
  arXiv  Detail & Related papers  (2025-03-12T05:05:58Z)
• SIC: Similarity-Based Interpretable Image Classification with Neural Networks [3.0248879829045388]
  We introduce SIC, a neural network that provides local and global explanations of its decision-making process.<n>We evaluate SIC on three tasks: fine-grained classification on Stanford Dogs and FunnyBirds, multi-label classification on Pascal VOC, and pathology detection on the RSNA dataset.
  arXiv  Detail & Related papers  (2025-01-28T22:39:03Z)
• Choose Your Explanation: A Comparison of SHAP and GradCAM in Human Activity Recognition [0.13194391758295113]
  This study compares Shapley Additive Explanations (SHAP) and Gradient-weighted Class Activation Mapping (Grad-CAM)<n>We quantitatively and quantitatively compare these methods, focusing on feature importance ranking, interpretability, and model sensitivity through perturbation experiments.<n>Our research demonstrates how SHAP and Grad-CAM could complement each other to provide more interpretable and actionable model explanations.
  arXiv  Detail & Related papers  (2024-12-20T15:53:25Z)
• Adversarial Vessel-Unveiling Semi-Supervised Segmentation for Retinopathy of Prematurity Diagnosis [9.683492465191241]
  We propose a semi supervised segmentation framework designed to advance ROP studies without the need for extensive manual vessel annotation. Unlike previous methods that rely solely on limited labeled data, our approach integrates uncertainty weighted vessel unveiling module and domain adversarial learning. We validate our approach on public datasets and an in-house ROP dataset, demonstrating its superior performance across multiple evaluation metrics.
  arXiv  Detail & Related papers  (2024-11-14T02:40:34Z)
• XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners [71.8257151788923]
  We propose a novel Explainable Active Learning framework (XAL) for low-resource text classification.<n>XAL encourages classifiers to justify their inferences and delve into unlabeled data for which they cannot provide reasonable explanations.<n>Experiments on six datasets show that XAL achieves consistent improvement over 9 strong baselines.
  arXiv  Detail & Related papers  (2023-10-09T08:07:04Z)
• Learning Common Rationale to Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems [61.11799513362704]
  We propose learning an additional screening mechanism to identify discriminative clues commonly seen across instances and classes. We show that a common rationale detector can be learned by simply exploiting the GradCAM induced from the SSL objective.
  arXiv  Detail & Related papers  (2023-03-03T02:07:40Z)
• NeuroExplainer: Fine-Grained Attention Decoding to Uncover Cortical Development Patterns of Preterm Infants [73.85768093666582]
  We propose an explainable geometric deep network dubbed NeuroExplainer. NeuroExplainer is used to uncover altered infant cortical development patterns associated with preterm birth.
  arXiv  Detail & Related papers  (2023-01-01T12:48:12Z)
• PCA: Semi-supervised Segmentation with Patch Confidence Adversarial Training [52.895952593202054]
  We propose a new semi-supervised adversarial method called Patch Confidence Adrial Training (PCA) for medical image segmentation. PCA learns the pixel structure and context information in each patch to get enough gradient feedback, which aids the discriminator in convergent to an optimal state. Our method outperforms the state-of-the-art semi-supervised methods, which demonstrates its effectiveness for medical image segmentation.
  arXiv  Detail & Related papers  (2022-07-24T07:45:47Z)
• Using Representation Expressiveness and Learnability to Evaluate Self-Supervised Learning Methods [61.49061000562676]
  We introduce Cluster Learnability (CL) to assess learnability. CL is measured in terms of the performance of a KNN trained to predict labels obtained by clustering the representations with K-means. We find that CL better correlates with in-distribution model performance than other competing recent evaluation schemes.
  arXiv  Detail & Related papers  (2022-06-02T19:05:13Z)
• The Overlooked Classifier in Human-Object Interaction Recognition [82.20671129356037]
  We encode the semantic correlation among classes into the classification head by initializing the weights with language embeddings of HOIs. We propose a new loss named LSE-Sign to enhance multi-label learning on a long-tailed dataset. Our simple yet effective method enables detection-free HOI classification, outperforming the state-of-the-arts that require object detection and human pose by a clear margin.
  arXiv  Detail & Related papers  (2022-03-10T23:35:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.