%Aigaion2 BibTeX export from Idiap Publications
%Sunday 21 July 2024 06:41:05 PM

@ARTICLE{Meegahapola_IMWUT_2022,
         author = {Meegahapola, Lakmal Buddika and Droz, William and de G{\"{o}}tzen, Amalia and KUN, PETER and Nuttakki, Chaitanya and Diwakar, Shyam and Ruiz-Correa, Salvador and Song, Donglei and Xu, Hao and Bidoglia, Miriam and Gaskell, George and Chagnaa, Altangerel and Ganbold, Amarsanaa and Zundui, Tsolmon and Caprini, Carlo and Miorandi, Daniele and Hume, Alethia and Zarza, Jos{\'{e}} Luis and Cernuzzi, Luca and Bison, Ivano and Britez, Marcelo Rodas and Busso, Matteo and Chenu-Abente, Ronald and Gunel, Can and Giunchiglia, Fausto and Schelenz, Laura and Gatica-Perez, Daniel},
       projects = {Idiap},
          month = dec,
          title = {Generalization and Personalization of Mobile Sensing-Based Mood Inference Models: An Analysis of College Students in Eight Countries},
        journal = {Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT)},
         volume = {6},
         number = {4},
           year = {2022},
            doi = {10.1145/3569483},
       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. Hence, 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, possibly due to the cultural similarity of European countries leading to similar phone sensor data. Overall, we uncover generalization issues of mood inference models to new countries and how the geographical/cultural similarity of countries impacts mood inference.},
            pdf = {https://publications.idiap.ch/attachments/papers/2022/Meegahapola_IMWUT_2022.pdf}
}