Understanding a happiness dataset: How the machine learning classification accuracy changes with different demographic groups

Sweeney, Colm; Ennis, Edel; Bond, Raymond; Mulvenna, Maurice; O’Neill, Siobhan

doi:10.1109/iscc53001.2021.9631455

Cited by 3 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, most mental health chatbots have been designed for depression and anxiety (Milne-Ives et al, 2020)among students (Milne-Ives et al, 2020;Klos et al, 2021), support children with autism (Cooper and Ireland, 2018), suicide risk, substance abuse (Prochaska et al, 2021), post-traumatic stress disorder (Han et al, 2021), and stress (Mauriello et al, 2021). They have also been used to enhance psychological well-being (Sweeney et al, 2021), self-compassion (Lee et al, 2019), and mindfulness (Denecke et al, 2021).…”

Section: Use Of Chatbotsmentioning

confidence: 99%

Reinventing mental health care in youth through mobile approaches: Current status and future steps

Marciano

Saboor²

2023

Front. Psychol.

View full text Add to dashboard Cite

In this perspective, we aim to bring together research on mobile assessments and interventions in the context of mental health care in youth. After the COVID-19 pandemic, one out of five young people is experiencing mental health problems worldwide. New ways to face this burden are now needed. Young people search for low-burden services in terms of costs and time, paired with high flexibility and easy accessibility. Mobile applications meet these principles by providing new ways to inform, monitor, educate, and enable self-help, thus reinventing mental health care in youth. In this perspective, we explore the existing literature reviews on mobile assessments and interventions in youth through data collected passively (e.g., digital phenotyping) and actively (e.g., using Ecological Momentary Assessments—EMAs). The richness of such approaches relies on assessing mental health dynamically by extending beyond the confines of traditional methods and diagnostic criteria, and the integration of sensor data from multiple channels, thus allowing the cross-validation of symptoms through multiple information. However, we also acknowledge the promises and pitfalls of such approaches, including the problem of interpreting small effects combined with different data sources and the real benefits in terms of outcome prediction when compared to gold-standard methods. We also explore a new promising and complementary approach, using chatbots and conversational agents, that encourages interaction while tracing health and providing interventions. Finally, we suggest that it is important to continue to move beyond the ill-being framework by giving more importance to intervention fostering well-being, e.g., using positive psychology.

show abstract

Section: Use Of Chatbotsmentioning

confidence: 99%

Reinventing mental health care in youth through mobile approaches: Current status and future steps

Marciano

Saboor²

2023

Front. Psychol.

View full text Add to dashboard Cite

show abstract

“…This paper is an extended and improved version of the original paper [5], which was presented at the ICTS4eHealth (IEEE International Conference on ICT Solutions for e-Health) workshop at the ISCC (IEEE Symposium on Computers and Communications (ISCC 2021) conference in September 2021. The main contributions of this extended paper include revised methods, the additional analysis of balanced data where new experiments were undertaken across three age groups and the original results were improved, and comparison with the new balanced samples using new line charts.…”

Section: Introductionmentioning

confidence: 99%

How Machine Learning Classification Accuracy Changes in a Happiness Dataset with Different Demographic Groups

et al. 2022

Self Cite

View full text Add to dashboard Cite

This study aims to explore how machine learning classification accuracy changes with different demographic groups. The HappyDB is a dataset that contains over 100,000 happy statements, incorporating demographic information that includes marital status, gender, age, and parenthood status. Using the happiness category field, we test different types of machine learning classifiers to predict what category of happiness the statements belong to, for example, whether they indicate happiness relating to achievement or affection. The tests were initially conducted with three distinct classifiers and the best performing model was the convolutional neural network (CNN) model, which is a deep learning algorithm, achieving an F1 score of 0.897 when used with the complete dataset. This model was then used as the main classifier to further analyze the results and to establish any variety in performance when tested on different demographic groups. We analyzed the results to see if classification accuracy was improved for different demographic groups, and found that the accuracy of prediction within this dataset declined with age, with the exception of the single parent subgroup. The results also showed improved performance for the married and parent subgroups, and lower performances for the non-parent and un-married subgroups, even when investigating a balanced sample.

show abstract

A Hybrid Approach for Happy Emotion Analysis through Partition and Voronoi-density based Clustering and DistilBERT

Agrawal,

Boggarapu,

Arya

2024

2024 IEEE 9th International Conference for Convergence in Technology (I2CT)

View full text Add to dashboard Cite

Understanding a happiness dataset: How the machine learning classification accuracy changes with different demographic groups

Cited by 3 publications

References 1 publication

Reinventing mental health care in youth through mobile approaches: Current status and future steps

Reinventing mental health care in youth through mobile approaches: Current status and future steps

How Machine Learning Classification Accuracy Changes in a Happiness Dataset with Different Demographic Groups

A Hybrid Approach for Happy Emotion Analysis through Partition and Voronoi-density based Clustering and DistilBERT

Contact Info

Product

Resources

About