The Best Paper Award at the UBICOMP
We are proud to share that the DataScientia scholars from the WeNet research team received a notable award at ACM UbiComp/ISWC 2023 in Cancún, Mexico! Their paper, “Generalization and Personalization of Mobile Sensing-Based Mood Interference Models: An Analysis of College Students in Eight Countries,” was honored with the “Distinguished Paper Award,” recognizing DataScientia’s outstanding contributions to mobile sensing research and data science. The article was also published in the Proceedings of the ACM on Interactive, Mobile, Wearable, and Ubiquitous Technologies (IMWUT).
The work was presented by Lakmal Meegahapola, the first author and Postdoc Researcher at ETH Zürich. Besides, he became one of the finalists in the top 4 in the rank of the ACM UbiComp Outstanding Student Award for his prominent academic input in persuasive computing. He demonstrated outstanding research performance in model personalization, generalization, and distribution shift. We congratulate Lakmal for being recognised for his exceptional contributions to persuasive computing and mobile health sensing!
Here is the paper’s abstract:
Mood inference with mobile sensing data has been studied in ubicomp literature over the last decade. This inference enables context-aware and personalized user experiences in general mobile apps and valuable feedback and interventions in mobile health apps. However, even though model generalization issues have been highlighted in many studies, the focus has always been on improving the accuracies of models using different sensing modalities and machine learning techniques, with datasets collected in homogeneous populations. In contrast, less attention has been given to studying the performance of mood inference models to assess whether models generalize to new countries.
In this study, we collected a mobile sensing dataset with 329K self-reports from 678 participants in eight countries (China, Denmark, India, Italy, Mexico, Mongolia, Paraguay, UK) to assess the effect of geographical diversity on mood inference models. We define and evaluate country-specific (trained and tested within a country), continent-specific (trained and tested within a continent), country-agnostic (tested on a country not seen on training data), and multi-country (trained and tested with multiple countries) approaches trained on sensor data for two mood inference tasks with population-level (non-personalized) and hybrid (partially personalized) models.
We show that partially personalized country-specific models perform the best yielding area under the receiver operating characteristic curve (AUROC) scores of the range 0.78–0.98 for two-class (negative vs. positive valence) and 0.76–0.94 for three-class (negative vs. neutral vs. positive valence) inference. Further, with the country-agnostic approach, we show that models do not perform well compared to country-specific settings, even when models are partially personalized. We also show that continent-specific models outperform multi-country models in the case of Europe. Overall, we uncover generalization issues of mood inference models to new countries and how the geographical similarity of countries might impact mood inference.
Read the full paper and download pdf here.
Keywords: mood inference, mobile sensing, model generalization, geographical diversity, context-aware applications, personalized user experiences, mobile health apps, sensor data, self-reports, machine learning, country-specific models, continent-specific models, country-agnostic models, multi-country models, non-personalized models, hybrid models, negative valence, positive valence, AUROC (Area Under Receiver Operating Characteristic curve), population-level inference, partially personalized models.
────────────────
Tetiana Bihun
Author, Content Creator
