<p> This work is an investigation of user acceptance of a prototype solution utilizing wireless text messaging (or SMS - i.e., short messaging service) to improve people's adherence. Insufficient adherence, also known as medical non-compliance, is a major cause of failure in self-management programs, causing significant losses to all healthcare stakeholders.</p> <p> Innovative mobile healthcare solutions, based on portable devices like cell phones, may address some non-adherence aspects by helping outpatients to follow treatments agreed with their health providers. Although this seems a win-win situation, a verdict on the overall usefulness of such an approach cannot be formulated before exploring outpatient acceptance, as this is a novel technology that targets a new area of implementation. Accordingly, this research investigates key factors that may influence the acceptance of a mobile healthcare solution based on SMS to support improved adherence to healthy behaviour, with special attention to motivation (the 'pro' factors) and perceived risk (the 'con' factors).</p> <p> As a means of investigation, a one-month longitudinal experiment with two groups of subjects (an intervention group and a control group) was utilized. Data were analyzed with quantitative and qualitative techniques: descriptive statistics, partial least squares modelling, and content analysis.</p> <p> Findings show that users are aware of the potential usefulness of such a pioneering application. However, enjoyment is the unique reason for adopting, and perceived financial and psychological risks the main obstacles against adopting, an SMS-based solution for improving adherence to healthy behaviour. Furthermore, a business analysis shows that users are concerned about usefulness features, even when asked about financial aspects.</p> <p> These results, together with encouraging findings about the effectiveness of the application, open the way for medical-led research to investigate if long-term mobile healthcare initiatives customized to patient needs are also beneficial for outpatient adherence and health outcomes.</p> / Thesis / Doctor of Philosophy (PhD)

京都大学 / 新制・課程博士 / 博士(情報学) / 甲第24928号 / 情博第839号 / 新制||情||141(附属図書館) / 京都大学大学院情報学研究科知能情報学専攻 / (主査)教授 森 信介, 教授 西野 恒, 教授 中村 裕一 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

The rapid growth of user-generated content on social media platforms in the form of text caused moderating toxic language manually to become an increasingly challenging task. Consequently, researchers have turned to artificial intelligence (AI) and machine learning (ML) models to detect and classify toxic comments automatically. However, these models often exhibit unintended bias against comments containing sensitive terms related to de- mographic groups, such as race and gender, which leads to unfair classifications of samples. In addition, most existing research on this topic focuses on fully supervised learning frame- works. Therefore, there is a growing need to explore fairness in semi-supervised toxicity detection due to the difficulty of annotating large amounts of data. In this thesis, we aim to address this gap by developing a fair generative-based semi-supervised framework for mitigating social bias in toxicity text classification. This framework consists of two parts, first, we trained a semi-supervised generative-based text classification model on the bench- mark toxicity datasets. Then, in the second step, we mitigated social bias in the trained classifier in step 1 using adversarial debiasing, to improve fairness. In this work, we use two different semi-supervised generative-based text classification models, NDAGAN and GANBERT (the difference between them is that the former adds negative data augmenta- tion to address some of the problems in GANBERT), to propose two fair semi-supervised models called FairNDAGAN and FairGANBERT. Finally, we compare the performance of the proposed fair semi-supervised models in terms of accuracy and fairness (equalized odds difference) against baselines to clarify the challenges of social fairness in semi-supervised toxicity text classification for the first time. Based on the experimental results, the key contributions of this research are: first, we propose a novel fair semi-supervised generative-based framework for fair toxicity text classification for the first time. Second, we show that we can achieve fairness in semi- supervised toxicity text classification without considerable loss of accuracy. Third, we demonstrate that achieving fairness at the coarse-grained level improves fairness at the fine-grained level but does not always guarantee it. Fourth, we justify the impact of the labeled and unlabeled data in terms of fairness and accuracy in the studied semi- supervised framework. Finally, we demonstrate the susceptibility of the supervised and semi-supervised models against data imbalance in terms of accuracy and fairness.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.