TZTianyi Zhang

Tianyi Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Tianyi Zhang has a total of 32 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Personality shapes how mobility patterns relate to perceived problematic smartphone use: A passive sensing study

    by Tianyi Zhang, Mathew Varidel, Ian Hickie, Nicholas Ho, Ashlee Turner, Simon D'ALfonso, Frank Iorfino

    Understanding problematic smartphone use remains limited, especially how behavioural patterns and individual differences shape smartphone addiction. Most existing research explores psychometric measures using relatively simple explanatory frameworks, with less known about behavioural signatures captured through passive sensing and their variations across personality traits. We investigated associations among passive sensing data, self-reported smartphone addiction, and personality using 119 days of passive sensing data from 151 university students, baseline Big Five Inventory measures and post-study Smartphone Addiction Scale – Short Version responses. Multiple linear regression models showed that smartphone usage intensity exhibits consistent associations with higher smartphone addiction. Location entropy and moving distance demonstrated personality-dependent effects. Greater smartphone addiction associated with lower moving distance among individuals higher in Extroversion (β = -0.38, SE = 0.12) and Neuroticism (β = -0.32, SE = 0.10), whereas this relationship was reversed among those higher in Conscientiousness (β = 0.30, SE, 0.11) and Agreeableness (β = 0.38, SE = 0.13). Higher location entropy was associated with lower smartphone addiction among those higher in Conscientiousness (β = -0.21, SE = 0.09) and Neuroticism (β = -0.24, SE = 0.10). These findings highlight personality-dependent behavioural markers of problematic smartphone use, supporting personalised mental health monitoring and just-in-time interventions.

  • Open Access

    Multi-Task Mental Health Detection with Large Language Models under Class Imbalance

    by Xiangyuan Xue, Tianyi Zhang, Vassilis Kostakos, Ting Dang, Hong Jia

  • Open Access

    NarrativeSense: Predicting Affective States in University Students through Smartphone Sensing and Contextual Narratives

    by Tianyi Zhang, Yan Li, Yihao Ding, Hong Jia, Vassilis Kostakos, Simon D’ALfonso

    Mental health challenges are increasingly prevalent among university students, yet often go undetected due to reliance on traditional assessments that are subjective, infrequent, and lack behavioral context. Digital phenotyping through passively collected smartphone data offers a scalable alternative, but existing approaches often fail to integrate predictive accuracy with narrative-based insights. To overcome these limitations, we present NarrativeSense, a novel framework that combines machine learning models with narrative-based descriptions of daily life events inferred from smartphone sensing data to predict weekly affective states. The system incorporates language model components to transform behavioral patterns into contextualized, human-readable narratives that ground affective predictions in everyday experiences. This narrative layer complements structured prediction by offering intuitive, user-centered insights. Applied to longitudinal data from 58 university students over 119 days, NarrativeSense outperforms baseline machine learning models, standalone LLMs, and ensemble methods, while providing richer insights. Our findings demonstrate the potential of narrative-enhanced digital phenotyping for scalable and explainable mental health monitoring in educational and clinical settings.

  • Open Access

    SmartSense-D: A safety, feasibility, and acceptability pilot study of digital phenotyping in young people with major depressive disorder

    by Andres Camargo, Scott D Tagliaferri, Simon D’aLfonso, Tianyi Zhang, Zamantha Munoz, Pemma Davies, Mario Alvarez-Jimenez, Niels van Berkel, Vassilis Kostakos, Lianne Schmaal

    Background: Digital assessment of behaviours, including physical activity, sleep, and social interactions could be associated with changes in mood and other mental health symptoms. This study assessed the safety, feasibility, acceptability, and potential predictive value of passive and active sensing in young people with major depressive disorder (MDD). Methods: Over eight weeks, passive (smartphone sensing, actigraphy) and active (ecological momentary assessment; EMA) data were collected from 40 young participants with MDD (aged 16–25 years). We assessed the safety, feasibility, and acceptability of daily active and passive sensing in this population. Additionally, linear mixed models and correlation analysis explored associations between passive and active sensing measures. Results: Of the 48 young participants, 83% (n = 40) completed the full protocol. No adverse events were reported. Over eight weeks, participants averaged 35.9 days (65.3%) with EMAs and 37.9 days (69%) with actigraphy data. Smartphone sensors recorded communication for 21.1 days (38.4%), location for 43.1 days (78.4%), maximum unlock duration for 43.4 days (79%), social media use for 34.8 days (63.3%), and inter-key delay for 32.8 days (59.6%). Regarding acceptability, 83.1% found the application usable and comfortable. Secondary measures showed significant correlations between sleep and physical activity, and between location and phone use sensors. There was a significant negative association between daily positive mood ratings and QIDS total scores (Beta coefficient [95% CI]: 2.66 [−3.98, −1.34]; p = 0.002). Conclusion: Passive and active sensing methods were safe, and acceptable among young people with MDD.


  • Open Access

    Nomophobia, Psychopathology, and Smartphone-Inferred Behaviors in Youth With Depression: Longitudinal Study

    by Tianyi Zhang, Andres Camargo, Lianne Schmaal, Vassilis Kostakos, Simon D'ALfonso

    Background: Smartphones have become an indispensable part of people’s lives, and the fear of being without them, what has been termed “no mobile phone phobia” (nomophobia), is a growing phenomenon. The rise of problematic smartphone use highlights the urgent need to explore the intricate relationship between smartphones and human behavior. However, the connections between nomophobia, mental health indicators, smartphone use patterns, and daily activities remain largely underexplored. Objective: This study aimed to explore the relationship between young adults with depression and smartphones and investigate nomophobia by analyzing data obtained from a pilot study of depression in a youth cohort. Exploring nomophobia can enhance our understanding of the dynamics between young adults and smartphone use, potentially empowering them to manage and regulate their smartphone use more effectively. Methods: During an 8-week period, data collected via smartphone sensors, such as locations and screen status, were gathered from a cohort of 41 individuals diagnosed with major depressive disorder. In addition to passive-sensing smartphone data, the study collected ecological momentary assessments and psychometric measures, including the Nomophobia Questionnaire, which formed the basis of our investigation. We explored statistical associations among smartphone-derived behavioral features, psychometric indicators, and nomophobia. In addition, we used behavioral and psychometric data to develop regression models demonstrating the prediction of nomophobia levels. Results: Our findings revealed that the level of nomophobia was positively associated with depression and negative affect, lower geolocation movements, and higher comfort with smartphone sensing. The exploratory predictive linear regression models demonstrated the feasibility of predicting an individual’s Nomophobia Questionnaire score based on their smartphone sensing data. These models effectively used input features derived from both a combination of smartphone sensing data and psychometric measures and from smartphone sensing data alone. Conclusions: Our work is the first to explore the relationship between nomophobia and smartphone sensor data. It provides valuable insights into the predictors of nomophobia level, contributing to the understanding of the relationship between smartphones and human behavior and paving the way for future studies.


  • Open Access

    AutoJournaling: A Context-Aware Journaling System Leveraging MLLMs on Smartphone Screenshots

    by Tianyi Zhang, Shiquan Zhang, Le Fang, Hong Jia, Vassilis Kostakos, Simon D'ALfonso

    Journaling offers significant benefits, including fostering self-reflection, enhancing writing skills, and aiding in mood monitoring. However, many people abandon the practice because traditional journaling is time-consuming, and detailed life events may be overlooked if not recorded promptly. Given that smartphones are the most widely used devices for entertainment, work, and socialization, they present an ideal platform for innovative approaches to journaling. Despite their ubiquity, the potential of using digital phenotyping, a method of unobtrusively collecting data from digital devices to gain insights into psychological and behavioral patterns, for automated journal generation has been largely underexplored. In this study, we propose AutoJournaling, the first-of-its-kind system that automatically generates journals by collecting and analyzing screenshots from smartphones. This system captures life events and corresponding emotions, offering a novel approach to digital phenotyping. We evaluated AutoJournaling by collecting screenshots every 3 seconds from three students over five days, demonstrating its feasibility and accuracy. AutoJournaling is the first framework to utilize seamlessly collected screenshots for journal generation, providing new insights into psychological states through digital phenotyping.


  • Open Access

    Leveraging LLMs to Predict Affective States via Smartphone Sensor Features

    by Tianyi Zhang, Songyan Teng, Hong Jia, Simon D'ALfonso

    As mental health issues for young adults present a pressing public health concern, daily digital mood monitoring for early detection has become an important prospect. An active research area, digital phenotyping, involves collecting and analysing data from personal digital devices such as smartphones (usage and sensors) and wearables to infer behaviours and mental health. Whilst this data is standardly analysed using statistical and machine learning approaches, the emergence of large language models (LLMs) offers a new approach to make sense of smartphone sensing data. Despite their effectiveness across various domains, LLMs remain relatively unexplored in digital mental health, particularly in integrating mobile sensor data. Our study aims to bridge this gap by employing LLMs to predict affect outcomes based on smartphone sensing data from university students. We demonstrate the efficacy of zero-shot and few-shot embedding LLMs in inferring general wellbeing. Our findings reveal that LLMs can make promising predictions of affect measures using solely smartphone sensing data. This research sheds light on the potential of LLMs for affective state prediction, emphasizing the intricate link between smartphone behavioral patterns and affective states. To our knowledge, this is the first work to leverage LLMs for affective state prediction and digital phenotyping tasks.