United States

Autonomy support is an interpersonal tone of support and understanding. Teachers&#39; instructional behaviors with autonomy support facilitate students&#39; inner motivational resources and enhance their engagement in learning activities. Identifying these behaviors is vital in terms of teaching effects on students&#39; academic performance and behaviors. However, existing methods heavily rely on psychological questionnaires or observers, which are time consuming and difficult to apply in large scale teaching scenarios. In this work, we combine deep neural networks with psychology to achieve automatically identifying the behaviors. To this end, we create the first Chinese instructional behavior dataset for deep learning, and then construct a BERT-based network for modeling psychological features and identifying behaviors. Since frequencies of different behaviors are highly imbalanced, we further design a novel loss function to adaptively optimize training weights for each behavior. Extensive experiments verify the effectiveness of our method and explain how the behaviors are identified.

CogSci 2023

Automatically Identifying Teachers&#39; Autonomy Support using Text Classification on Imbalanced Data

Autonomy support is an interpersonal tone of support and understanding. Teachers' instructional behaviors with autonomy support facilitate students' inner motivational resources and enhance their engagement in learning activities. Identifying these behaviors is vital in terms of teaching effects on students' academic performance and behaviors. However, existing methods heavily rely on psychological questionnaires or observers, which are time consuming and difficult to apply in large scale teaching scenarios. In this work, we combine deep neural networks with psychology to achieve automatically identifying the behaviors. To this end, we create the first Chinese instructional behavior dataset for deep learning, and then construct a BERT-based network for modeling psychological features and identifying behaviors. Since frequencies of different behaviors are highly imbalanced, we further design a novel loss function to adaptively optimize training weights for each behavior. Extensive experiments verify the effectiveness of our method and explain how the behaviors are identified.

Automatically Identifying Teachers' Autonomy Support using Text Classification on Imbalanced Data

poster

The 45th Annual Meeting of the Cognitive Science Society will take place in Sydney, Australia as a modified hybrid conference. Presentations from the main-session room will be live-streamed every day for all events. This will include all invited talks and award sessions. Recordings of all CogSci 2023 sessions will be made available for on-demand viewing after the conference.<br>
The in-person component will be held at the International Convention Centre Sydney at Darling Harbour. The Conference will take place Wednesday July 26th – Saturday July 29th, 2023 (Wednesday, July 26th is the Workshops Day).

Join us!

<br>[**The Program at a Glance can be found here**](https://cognitivesciencesociety.org/wp-content/uploads/2023/07/COgSci-PAAG-V2.pdf)
<br>[**The Detailed Program can be found here**](https://online.fliphtml5.com/ebtyf/mswz/)
<br><br>

#### **CogSci 2023 Program Book**
<iframe style="width:700px;height:400px" src="https://online.fliphtml5.com/ebtyf/tzgk/"  seamless="seamless" scrolling="no" frameborder="0" allowtransparency="true" allowfullscreen="true" ></iframe>
<br>

The 45th Annual Meeting of the Cognitive Science Society presents the latest research across cognitive science and highlights the theme of Cognition in Context.

We propose the predictive forward-forward (PFF) algorithm for conducting credit assignment in neural systems. Specifically, we design a novel, dynamic recurrent neural system that learns a directed generative circuit jointly and simultaneously with a representation circuit, integrating learnable lateral competition and elements of predictive coding, an emerging and viable neurobiological process theory of cortical function, with the forward-forward (FF) adaptation scheme. Furthermore, PFF efficiently learns to propagate learning signals and updates synapses with forward passes only, eliminating key structural and computational constraints imposed by a backprop-based scheme. Besides computational advantages, the PFF process could prove useful for understanding the learning mechanisms behind biological neurons that use local signals despite missing feedback connections. We run experiments on image data and demonstrate that the PFF procedure works as well as backprop, offering a promising brain-inspired learning algorithm for classifying, reconstructing, and synthesizing data patterns.

The Predictive Forward-Forward Algorithm

Sentiment and emotion embody intrinsic experience of human cognition, both of which have the profoundly influence on the cognitive processes in humans. The commonality between sentiment and emotion leads to the fact that sentiment classification and emotion recognition are two correlated tasks in cognitive science and artifical intellignce (AI). One task improves its performance by leveraging similarities and differences across tasks. However, recent works have often treated them as two separately different tasks, where their commonalities have largely been neglected. To fill this gap, we propose a multi-task interactive graph attention network with position encodings, termed MIP-GAT. The main proposal is a multi-interactive graph interaction layer where a syntactic dependency connection, a cross-task connection and position encodings are constructed and incorporated into a unified graphical structure. Empirical evaluation on two benchmarking datasets, i.e., CMU-MOSEI and GoEmotions, shows the effectiveness of the proposed model over state-of-the-art baselines. In addition, we also explore the superiority and limitations of the proposed model.

MIP-GAT: A Multi-Task Interactive Graph Attention Network with Position Encodings for Joint Sentiment Classification and Emotion Recognition

Humans can successfully interpret images even when they have been distorted by significant image transformations. Such images aid in differentiating existing computational models for perception because models which predict similar results for typical stimuli that may diverge when confronted with atypical stimuli. In this work, we propose an explanation of people's ability to perceive a specific class of degraded stimuli that requires extreme generalization capabilities: Mooney, or two-tone, faces. We provide a parametric and controllable method to generate Mooney faces and a hypothesis about how the human visual system might be able to perceive such extreme precepts. We show that Mooney faces can be approximated under extreme illumination conditions; a computer graphics perspective on the Mooney image formation process suggests inverse graphics as a model for perceptual generalization and possibly everyday perception. With various visual examples, we argue that Mooney faces are important in the understanding the role of generative models and inverse graphics in human visual processing.

Perception of Mooney Faces: Extreme Generalization through Inverse Rendering?

Cross-lingual adaptation has shown effectiveness in low-resource spoken language understanding (SLU) systems.
However, existing approaches often show unsatisfactory performance on intent detection and slot filling, especially for distant languages,
which are dramatically different from source language in scripts, morphology, or syntax.
To solve the aforementioned challenges, we propose Latent Dialogue Action (LaDA) layer to 
optimize decoding strategy.
The model consists of an extra latent dialogue action layer. It enables our model to enhance a system’s ability to
handle conversations in complex multi-lingual intent and slot value of distant languages.
To our best knowledge, our work is the first
comprehensive study of the use of latent variables for cross-lingual SLU
policy optimization during decode stage. LaDA
achieves state-of-the-art results in zero-shot and few-shot adaptation both on public datasets.

LaDA: Latent Dialogue Action For Zero-shot Cross-lingual Neural Network Language Modeling

In this work, we propose an interpretable knowledge tracking model (KVFKT) based on key value and forgetting. This model maintains the students’ knowledge state matrix in each memory unit, and also maintains the corresponding forgetting matrix to track the last review timestamp of students’ knowledge points. In addition, this model introduces the IRT two parameter model from the perspective of educational psychology to further enhance the interpretability of the model. Finally, the model is tested on four real-world datasets, and the experimental results prove the advantages of the method described in this paper.

An Interpretable Model With Forgetting Matrix For Deep Knowledge Tracking

The unprecedented spread of smartphone usage and its various boarding sensors have been garnering increasing interest in automatic mental health detection. However, there are two major barriers to reliable mental health detection applications that can be adopted in real-life: (a)The outputs of the complex machine learning model are not explainable, which reduces the trust of users and thus hinders the application in real-life scenarios. (b)The sensor signal distribution discrepancy across individuals is a major barrier to accurate detection since each individual has their own characteristics. We propose an explainable mental health detection model. Spatial and temporal features of multiple sensory sequences are extracted and fused with different weights generated by the attention mechanism so that the discrepancy of contribution to classifiers across different modalities can be considered in the model. Through a series of experiments on real-life datasets, results show the effectiveness of our model compared to the existing approaches.

Personalized multi-task attention for multimodal mental health detection and explanation

Thousands of learners are taking massive Open Online courses (MOOCs) in search of learning and self-improvement opportunities. However, the learning process often involves a struggle with confusion, which can adversely affect the course participation experience, leading to dropout halfway through. At the same time, it is impossible for the instructors to recognize and respond “confusion” posts from all posts accurately and timely, due to the large volume of registrants. This study identifies "confusion" posts that require instructors' attention through the BERT-CNN model and performs an attribution analysis of confusion based on the visualization results of confusion types and language features. We find that posts identified as "confused" actually represent different information needs of learners, which are mainly related to cognitive and social processes. Furthermore, we evaluated the BERT-CNN model with a 13% improvement in F1 value compared to previous studies and successfully applied it across unseen domains.

Feature Visualization and Attribution Analysis of Confusion for Massive Open Online Course

Behavior Trees (BTs) are widely used in many games, however, they are normally designed in a static way which is hard to deal with dynamic environments. One of the factors that restrict the performance of BTs is the optimization of resources used among sub-tasks, which has not been paid much attention. In this paper, we concentrate on the problem of dynamic allocation of agents for BTs, i.e., an important resource in games. We design a novel hierarchical learning framework, including the allocation learning module and the action learning module, to find strategies for agent allocation and action selection. Each agent is associated with a network for encoding observations, which is then assigned to a sub-task by the allocation learning network. Each sub-task uses a network to compute the action for the corresponding agent. We design how the losses are computed for the two modules respectively and present the whole training procedure. Finally, we examine the performance of the proposed framework on a well-known game, i.e., Google Research Football. The results show that each module works effectively and the whole framework improves the performance of BTs greatly. This work will have an important significance for the community of the usage of BTs.

Dynamic Agent Allocation with Reinforcement Learning for Applying Behavior Trees in Games

Despite increased interest in creating more diverse and inclusive organizational environments, scholars still have relatively little understanding of the cognitive mechanisms underlying leadership formation and how biases against marginalized groups are learned and maintained. Drawing from leadership emergence theory, we investigate potential interventions that support diverse leaders. Using agent-based simulations, we model a collective search process on a fitness landscape. Agents combine individual and social learning, and are represented as a feature vector blending relevant (e.g., individual learning characteristics) and irrelevant (e.g., race or gender) traits. Agents learn how to weigh the traits of others on the basis of reward expectations and dynamically adjust the connections of their social network to grant leadership. By initializing the network to privilege agents with irrelevant traits, we can create biases in how agents weigh certain traits. This framework allows us to test interventions to unlearn bias in favor of performance-relevant traits.

Unlearning the bias: An agent-based simulation for increasing diverse representation through leadership emergence

The ability to detect and analyze a human figure is key to our survival and social interactions. Efficient and robust identification of body parts can help to interpret images when bodies are partially occluded. While previous studies emphasized the configural processing of whole bodies using simplified stimuli, it still remains unclear how local contexts about body parts are integrated to resolve ambiguities (e.g., from occlusion) regarding the identities of or spatial relations among body parts. In a series of online experiments, we asked human observers to identify one ambiguous target body part in the presence of another “context” part. Our results showed that humans can use various amounts of spatial context to discount local ambiguities in natural images of pairs of parts, and are sensitive to low- and mid-level cues such as alignment and connectedness. Further simulations using computational models showed that the models with pairwise relational knowledge based on local part appearances failed to capture human sensitivity to relational properties of spatial context between pairs of body parts. Our results provided behavioral evidence in the human visual representations of various spatial relations between pairs of body parts and revealed different representations of spatial context used in humans and models.

Premium content

Automatically Identifying Teachers' Autonomy Support using Text Classification on Imbalanced Data

Next from CogSci 2023

The Predictive Forward-Forward Algorithm

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES