Information Processing and Overload in Group Conversation: A Graph-Based Prediction Model

Gabriel Murray

doi:10.3390/mti3030046

Abstract

Based on analyzing verbal and nonverbal features of small group conversations in a task-based scenario, this work focuses on automatic detection of group member perceptions about how well they are making use of available information, and whether they are experiencing information overload. Both the verbal and nonverbal features are derived from graph-based social network representations of the group interaction. For the task of predicting the information use ratings, a predictive model using random forests with verbal and nonverbal features significantly outperforms baselines in which the mean or median values of the training data are predicted, as well as significantly outperforming a linear regression baseline. For the task of predicting information overload ratings, the multimodal random forests model again outperforms all other models, including significant improvement over linear regression and gradient boosting models. However, on that task the best model is not significantly better than the mean and median baselines. For both tasks, we analyze performance using the full multimodal feature set versus using only linguistic features or only turn-taking features. While utilizing the full feature set yields the best performance in terms of mean squared error (MSE), there are no statistically significant differences, and using only linguistic features gives comparable performance. We provide a detailed analysis of the individual features that are most useful for each task. Beyond the immediate prediction tasks, our more general goal is to represent conversational interaction in such a way that yields a small number of features capturing the group interaction in an easily interpretable manner. The proposed approach is relevant to many other group prediction tasks as well, and is distinct from both classical natural language processing (NLP) as well as more current deep learning/artificial neural network approaches.

Highlights

Being able to tell whether a small group is making full use of available information, or whether they are experiencing information overload, is a valuable skill for a team leader or manager.Information overload—receiving too much information—is associated with lower job satisfaction and higher stress levels [1]
On the information use prediction task, the combined verbal and nonverbal features yield predictive performance that is significantly better than the performance of baselines that predict the mean or median values from the training data
One initial finding is that the information use prediction task is easier than the information overload task, as exhibited by the overall lower mean squared error (MSE) scores

Summary

Introduction

Being able to tell whether a small group is making full use of available information, or whether they are experiencing information overload, is a valuable skill for a team leader or manager.Information overload—receiving too much information—is associated with lower job satisfaction and higher stress levels [1]. Being able to tell whether a small group is making full use of available information, or whether they are experiencing information overload, is a valuable skill for a team leader or manager. Being able to automatically detect these information processing states would be a useful feature of a virtual meeting assistant Such a system could be utilized in real-time during a meeting in order to improve information processing and group effectiveness, or offline as a way of tracking team dynamics or auditing a decision that was made [2]. Features are derived from both graph representations and used to predict two outcome variables: whether the group members (in aggregate) felt that they made good use of all available information during their meeting, and whether they suffered from information overload during the meeting

Objectives

Methods

Results

Conclusion