Recovering individual emotional states from sparse ratings using collaborative filtering

TL;DR

This paper introduces a collaborative filtering method to accurately recover dense emotional ratings from sparse data, enabling high-resolution emotion measurement without disrupting natural emotional processes.

Contribution

It presents a novel application of collaborative filtering in emotion research, validated across diverse experimental contexts, and provides an open-source Python toolbox for implementation.

Findings

CF outperforms mean imputation in recovering missing emotional data

The approach accurately reconstructs dense ratings from sparse samples across various tasks

It enables high-dimensional emotion measurement with minimal disruption

Abstract

A fundamental challenge in emotion research is measuring feeling states with high granularity and temporal precision without disrupting the emotion generation process. Here we introduce and validate a new approach in which responses are sparsely sampled and the missing data are recovered using a computational technique known as collaborative filtering (CF). This approach leverages structured covariation across individual experiences and is available in Neighbors, an open-source Python toolbox. We validate our approach across three different experimental contexts by recovering dense individual ratings using only a small subset of the original data. In dataset 1, participants (n=316) separately rated 112 emotional images on 6 different discrete emotions. In dataset 2, participants (n=203) watched 8 short emotionally engaging autobiographical stories while simultaneously providing moment-by-moment ratings of the intensity of their affective experience. In dataset 3, participants (n=60) with distinct social preferences made 76 decisions about how much money to return in a hidden multiplier trust game. Across all experimental contexts, CF was able to accurately recover missing data and importantly outperformed mean imputation, particularly in contexts with greater individual variability. This approach will enable new avenues for affective science research by allowing researchers to acquire high dimensional ratings from emotional experiences with minimal disruption to the emotion-generation process.