Sofia Yfantidou

Sofia Yfantidou

Auto-generated profile, based on publicly available information

Sofia Yfantidou

Aristotle University of Thessaloniki

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 October 2022 in Scientific Data
Verified
Journal Article
Open access
PDF file
SYSofia Yfantidou
Sofia Yfantidou
CKChristina Karagianni
Christina Karagianni
SEStefanos Efstathiou
Stefanos Efstathiou
AVAthena Vakali
Athena Vakali
JPJoao Palotti
Joao Palotti
ŠGŠarūnas Girdzijauskas
Šarūnas Girdzijauskas
Ubiquitous self-tracking technologies have penetrated various aspects of our lives, from physical and mental health monitoring to fitness and entertainment. Yet, limited data exist on the association between in the wild large-scale physical activity patterns, sleep, stress, and overall health, and behavioral and psychological patterns due to challenges in collecting and releasing such datasets, including waning user engagement or privacy considerations. In this paper, we present the LifeSnaps dataset, a multi-modal, longitudinal, and geographically-distributed dataset containing a plethora of anthropological data, collected unobtrusively for the total course of more than 4 months by n = 71 participants. LifeSnaps contains more than 35 different data types from second to daily granularity, totaling more than 71 M rows of data. The participants contributed their data through validated surveys, ecological momentary assessments, and a Fitbit Sense smartwatch and consented to make these data available to empower future research. We envision that releasing this large-scale dataset of multi-modal real-world data will open novel research opportunities and potential applications in multiple disciplines.

31 July 2023 in ACM Transactions on Computing for Healthcare
Verified
Journal Article
Open access
SYSofia Yfantidou
Sofia Yfantidou
PSPavlos Sermpezis
Pavlos Sermpezis
AVAthena Vakali
Athena Vakali
In today’s connected society, many people rely on mHealth and self-tracking (ST) technology to help them adopt healthier habits with a focus on breaking their sedentary lifestyle and staying fit. However, there is scarce evidence of such technological interventions’ effectiveness, and there are no standardized methods to evaluate their impact on people’s physical activity and health. This work aims to help ST practitioners and researchers by empowering them with systematic guidelines and a framework for designing and evaluating technological interventions to facilitate health behavior change and user engagement, focusing on increasing physical activity and decreasing sedentariness. To this end, we conduct a literature review of 129 papers between 2008 and 2022, which identifies the core ST design principles and their efficacy, as well as the most comprehensive list to date of user engagement evaluation metrics for ST. Based on the review’s findings, we propose PAST SELF, a framework to guide the design and evaluation of ST technology that has potential applications in industrial and scientific settings. Finally, to facilitate researchers and practitioners, we complement this article with an open corpus and an online, adaptive exploration tool for the PAST SELF data.

27 September 2023 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Verified
Journal Article
Open access
SYSofia Yfantidou
Sofia Yfantidou
PSPavlos Sermpezis
Pavlos Sermpezis
AVAthena Vakali
Athena Vakali
RBRicardo Baeza-Yates
Ricardo Baeza-Yates
Personal informatics (PI) systems, powered by smartphones and wearables, enable people to lead healthier lifestyles by providing meaningful and actionable insights that break down barriers between users and their health information. Today, such systems are used by billions of users for monitoring not only physical activity and sleep but also vital signs and women's and heart health, among others. Despite their widespread usage, the processing of sensitive PI data may suffer from biases, which may entail practical and ethical implications. In this work, we present the first comprehensive empirical and analytical study of bias in PI systems, including biases in raw data and in the entire machine learning life cycle. We use the most detailed framework to date for exploring the different sources of bias and find that biases exist both in the data generation and the model learning and implementation streams. According to our results, the most affected minority groups are users with health issues, such as diabetes, joint issues, and hypertension, and female users, whose data biases are propagated or even amplified by learning models, while intersectional biases can also be observed.

28 April 2024 in Tourism and Hospitality
Verified
Journal Article
Open access
PDF file
GYGeorgia Yfantidou
Georgia Yfantidou
SYSofia Yfantidou
Sofia Yfantidou
DKDimitra Karanatsiou
Dimitra Karanatsiou
ALAngelos Liontakis
Angelos Liontakis
MMMairi Maniopoulou
Mairi Maniopoulou
VVVassiliki Vassilopoulou
Vassiliki Vassilopoulou
Fishing tourism, a niche yet burgeoning sector within the broader tourism industry, presents a unique opportunity to explore the dynamics of the Experience Economy. This study delves into the intricacies of fishing tourism through the lens of data science, leveraging web crawling techniques to gather extensive data from reviewer profiles on TripAdvisor. By employing natural language processing (NLP) techniques, the study investigates the correlation between Experience Economy dimensions and user profiling aspects within this domain. The findings of this study shed light on the predominant dimensions of the Experience Economy within fishing tourism. “Entertainment” emerges as the primary dimension, closely followed by “Aesthetic”, “Educational”, and “Escapist” elements. Notably, the study reveals frequent co-occurrences of certain dimension pairs, such as “Entertainment”–“Aesthetic” and “Educational”–“Entertainment”, underscoring the multifaceted nature of the fishing tourism experience. The implications of this research extend beyond academic discourse to practical considerations for stakeholders in the fishing tourism sector. By highlighting the socioeconomic benefits inherent in fishing tourism for local communities and fishers, the study emphasizes the importance of governmental support. This support, in the form of infrastructure development, effective leadership, legislative measures, and financial backing, is deemed essential for fostering sustainable growth and development in this sector. This study stands as a pioneering endeavor within the realm of fishing tourism research, particularly in its focus on Experience Economy dimensions and user profiling. By drawing data from both business pages and user profiles on TripAdvisor, it provides a comprehensive understanding of the intricate interplay between tourist experiences and the broader economic and social landscape of fishing tourism destinations.

24 August 2024
Verified
Conference Paper
Open access
SYSofia Yfantidou
Sofia Yfantidou
DSDimitris Spathis
Dimitris Spathis
MCMarios Constantinides
Marios Constantinides
AVAthena Vakali
Athena Vakali
DQDaniele Quercia
Daniele Quercia
FKFahim Kawsar
Fahim Kawsar
Self-supervised learning (SSL) has become the de facto training paradigm of large models, where pre-training is followed by supervised fine-tuning using domain-specific data and labels. Despite demonstrating comparable performance with supervised methods, comprehensive efforts to assess SSL's impact on machine learning fairness (i.e., performing equally on different demographic breakdowns) are lacking. Hypothesizing that SSL models would learn more generic, hence less biased representations, this study explores the impact of pre-training and fine-tuning strategies on fairness. We introduce a fairness assessment framework for SSL, comprising five stages: defining dataset requirements, pre-training, fine-tuning with gradual unfreezing, assessing representation similarity conditioned on demographics, and establishing domain-specific evaluation processes. We evaluate our method's generalizability on three real-world human-centric datasets (i.e., MIMIC, MESA, and GLOBEM) by systematically comparing hundreds of SSL and fine-tuned models on various dimensions spanning from the intermediate representations to appropriate evaluation metrics. Our findings demonstrate that SSL can significantly improve model fairness, while maintaining performance on par with supervised methods-exhibiting up to a 30% increase in fairness with minimal loss in performance through self-supervision. We posit that such differences can be attributed to representation dissimilarities found between the best- and the worst-performing demographics across models-up to x13 greater for protected attributes with larger performance discrepancies between segments. Code: https://github.com/Nokia-Bell-Labs/SSLfairness

19 October 2025
Verified
Book Chapter
Open access
PDF file
EPEva Paraschou
Eva Paraschou
IAIoannis Arapakis
Ioannis Arapakis
SYSofia Yfantidou
Sofia Yfantidou
SMSebastian Macaluso
Sebastian Macaluso
AVAthena Vakali
Athena Vakali
Artificial Intelligence (AI) is rapidly embedded in critical decision-making systems, however their foundational “black-box” models require eXplainable AI (XAI) solutions to enhance transparency, which are mostly oriented to experts, making no sense to non-experts. Alarming evidence about AI’s unprecedented human values risks brings forward the imperative need for transparent human-centered XAI solutions. In this work, we introduce a domain-, model-, explanation-agnostic, generalizable and reproducible framework that ensures both transparency and human-centered explanations tailored to the needs of both experts and non-experts. The framework leverages Large Language Models (LLMs) and employs in-context learning to convey domain- and explainability-relevant contextual knowledge into LLMs. Through its structured prompt and system setting, our framework encapsulates in one response explanations understandable by non-experts and technical information to experts, all grounded in domain and explainability principles. To demonstrate the effectiveness of our framework, we establish a ground-truth contextual “thesaurus” through a rigorous benchmarking with over 40 data, model, and XAI combinations for an explainable clustering analysis of a well-being scenario. Through a comprehensive quality and human-friendliness evaluation of our framework’s explanations, we prove high content quality through strong correlations with ground-truth explanations (Spearman rank correlation = 0.92) and improved interpretability and human-friendliness to non-experts through a user study (N = 56). Our overall evaluation confirms trust in LLMs as HCXAI enablers, as our framework bridges the above Gaps by delivering (i) high-quality technical explanations aligned with foundational XAI methods and (ii) clear, efficient, and interpretable human-centered explanations for non-experts.