Search

Digital technologies such as chatbots can be used in the field of mental health. In particular, chatbots can be used to support citizens living in sparsely populated areas who face problems such as poor access to mental health services, lack of 24/7 support, barriers to engagement, lack of age appropriate support and reductions in health budgets. The aim of this study was to establish if user groups can design content for a chatbot to support the mental wellbeing of individuals in rural areas. University students and staff, mental health professionals and mental health service users (N = 78 total) were recruited to workshops across Northern Ireland, Ireland, Scotland, Finland and Sweden. The findings revealed that participants wanted a positive chatbot that was able to listen, support, inform and build a rapport with users. Gamification could be used within the chatbot to increase user engagement and retention. Content within the chatbot could include validated mental health scales and appropriate response triggers, such as signposting to external resources should the user disclose potentially harmful information or suicidal intent. Overall, the workshop participants identified user needs which can be transformed into chatbot requirements. Responsible design of mental healthcare chatbots should consider what users want or need, but also what chatbot features artificial intelligence can competently facilitate and which features mental health professionals would endorse.

BACKGROUND In recent years, advances in technology have led to an influx of mental health apps, in particular the development of mental health and wellbeing chatbots which have already shown promise in terms of their efficacy, availability and accessibility. The ChatPal chatbot was developed to promote positive mental wellbeing amongst citizens living in rural areas. ChatPal is a multilingual chatbot, available in English, Scottish Gaelic, Swedish and Finnish, containing psychoeducational content and exercises such as mindfulness and breathing, mood logging, gratitude and thoughts diaries. OBJECTIVE The primary objective of this study is to establish if using a multilingual mental health and wellbeing chatbot (ChatPal) has an effect on mental wellbeing. Secondary objectives include characterising individuals whose wellbeing improved or declined, and applying thematic analysis to the user feedback. METHODS Participants were recruited to use the chatbot over a 12-week trial period. ChatPal was trialled in five regions; Northern Ireland, Scotland, Republic of Ireland, Sweden and Finland. Outcome measures included the Short Warwick Edinburgh Mental Wellbeing Scale, World Health Organisation-Five Well-Being Index, and Satisfaction with Life Scale, which were recorded at baseline, midpoint and end-point. Written feedback was collected from participants throughout the trial and subjected to qualitative analysis to identify themes. RESULTS A total of 348 people were recruited to the trial (75% female, 25% male) aged between 18-73 (mean age 30). The wellbeing scores of participants improved from baseline to midpoint and from baseline to end-point, however improvement in scores were not statistically significant on the Short Warwick Edinburgh Mental Wellbeing Scale (P=.42), World Health Organisation-Five Well-Being Index (P=.52), or Satisfaction with Life Scale (P=.81). Individuals that did show improvements in wellbeing (n=16) interacted more with the chatbot and were significantly younger compared (average 27 years old) to those whose wellbeing declined over the trial. Three themes were identified from user feedback including ‘positive experiences’, ‘mixed/ neutral experiences’ and ‘negative experiences’. Positive experiences mentioned enjoying exercises provided by the app, while most of the mixed/ neutral or negative experiences mentioned liking the chatbot overall, but that there were some barriers, such as technical or performance errors which needed to be overcome. CONCLUSIONS This paper further supports the need for blended service offerings. Marginal improvements in mental wellbeing were seen in those who used ChatPal (albeit non significant), so we propose that the chatbot could be used along with different service offerings to complement other digital or face-to-face services.

BACKGROUND Conversational user interfaces, or chatbots, are becoming more popular in the realm of digital health and wellbeing. Whilst many studies focus on measuring the cause of effect of a digital intervention on people's health and wellbeing (outcomes), there is a need to understand how users really engage and use a digital intervention in the real world. OBJECTIVE In this study we examine the user logs of a mental wellbeing chatbot called ChatPal, which is based on the concept of positive psychology. The aim of this research is to analyse the log data from the chatbot to provide insight into usage patterns, the different types of users using clustering, and associations between the usage of the application’s features. METHODS Log data from ChatPal was analysed to explore usage. A number of user characteristics including user tenure, unique days, mood logs recorded, conversations accessed, and total number of interactions were used with k-means clustering to identify user archetypes. Association rule mining was used to explore links between conversations. RESULTS ChatPal log data revealed 579 individuals over the age of 18 used the application with most users being female (67%). User interactions peaked around breakfast, lunchtime, and early evening. Clustering revealed three groups including ‘abandoning users’ (n=473), ‘sporadic users’ (n=93) and ‘frequent transient users’ (n=13). Each cluster had distinct usage characteristics, and the features were significantly different (P CONCLUSIONS This study has provided insight into the types of people using the ChatPal chatbot, patterns of use and associations between the usage of the application’s features which can be used to further develop the application by considering the features most accessed by users. CLINICALTRIAL

The objective of this study was to understand the attitudes of professionals who work in mental health regarding the use of conversational user interfaces, or chatbots, to support people’s mental health and wellbeing. This study involves an online survey to measure the awareness and attitudes of mental healthcare professionals and experts. The findings from this survey show that more than half of the participants in the survey agreed that there are benefits associated with mental healthcare chatbots (65%, p < 0.01). The perceived importance of chatbots was also relatively high (74%, p < 0.01), with more than three-quarters (79%, p < 0.01) of respondents agreeing that mental healthcare chatbots could help their clients better manage their own health, yet chatbots are overwhelmingly perceived as not adequately understanding or displaying human emotion (86%, p < 0.01). Even though the level of personal experience with chatbots among professionals and experts in mental health has been quite low, this study shows that where they have been used, the experience has been mostly satisfactory. This study has found that as years of experience increased, there was a corresponding increase in the belief that healthcare chatbots could help clients better manage their own mental health. Godkänd;2022;Nivå 0;2022-02-04 (johcin)

Sentiment analysis (SA) plays an important role in inferring sentiment or emotion from text and visual contents, such as images and videos to determine the overall contextual polarity of a document. Today, image recognition and classification are rapidly growing fields in the area of machine learning (ML). This paper presents a review of open-source machine learning algorithms, built using neural network-based frameworks such as TensorFlow and Keras, to serve as a benchmark for bespoke SA algorithms. This research also advocates open-source scikit-learn models for text tweets and image classification.Two prominent, publicly available and manually annotated benchmark text and image datasets were used to enable and assist in the correlation of this work with existing, present and future avant-garde and innovative methods. Quantitative results across four statistical criteria, including precision, recall, F1-score and accuracy compare favourably to the often complicated and tailored state-of-the-art methodologies developed. For SA, empirical results suggest deep-learning model frameworks to outperform scikit-learn algorithms. All experiments were conducted on computer hardware comprising 64GB of RAM and a NVIDEA GeForce RTX 2080 Ti GPU.

The Internet of Things (IoT) offers opportunities for data collection, processing and visualisation driving fruitful mechanisms for the demonstration and execution of STEM activities. Nevertheless its application in a primary school setting is not straightforward. There are issues ranging from the capability to setup an IoT system in the class, sound knowledge of technical terminology, relevancy to curriculum and finally the provision of a positive experience to students. In this paper we discuss our experiences including lessons learnt towards providing an IoT platform for STEM promotion in primary schools, the challenges identified and the solutions formed to tackle them. The outcome, is a set of practices for making IoT practically applicable for STEM activities.

The increased computational power of modern embedded devices with the widespread development of Internet infrastructure has brought the Internet of Things (IoT) era closest than ever. Recent market researches indicate that IoT product and relevant service suppliers will generate revenue exceeding $300 billion and the interconnected devices will grow to 26 billion [1, 2]. One field that can be benefited from the common advantages of IoT systems, (real time monitoring, large scale deployment etc.) is the Logistics area. In this paper we investigate a common problem in the logistics which is the automating object counting. We concentrate on uniform, disposable products stored on a pile, queue or a stack (e.g., a shelf) and examine a number of different technologies for sensing input and output through a gate to the storage area and how we can integrate them in an IoT environment. We define a set of comparison criteria with practical flavor in order to examine and evaluate twelve different types of sensors 3. The intention for our study is to form a baseline for anyone needing to implement gate-based input/output control.

Smart glasses have lately been under the spotlight for a variety of technical and usability reasons. Despite the current (early 2015) freeze of Google Glass sales, the area is active with other big companies involved in the development of smart glass devices-at the same time remains in early stages and fragmented. We undertake a technical study of these devices in order to identify trends and provide a classification to be used as a technical reference by application designers and developers. Our criteria are technical and range from the existence of an SDK to network connectivity and types of sensors.

While technical internships as a scheme are considered positive for both the intern and the hosting organisation, carrying out a successful internship session is not neither easy nor trivial. Towards managing an internship, we adopt an Agile-based framework that consists of four phases with a mixture of research, technical and communication tasks and covers the full project lifecycle providing good exposure to a range of professional practices. This framework is flexible to accommodate changes in preferences of an intern and includes a large variety of communication tasks such as project plan generation, technical progress reporting, generation and presentation of ideas and competitive analysis, along with technical tasks for instance Test Driven design and programming, development with C++ and code revision. Apart from interns, the hosting body benefits from the work of the interns which is reliable and of acceptable quality.

Although internships contribute to the professional development of a junior engineer, it is not straightforward to achieve a fruitful outcome for either the intern or the hosting the organisation. We discuss a structured framework based on Agile and Scrum concepts with the goal of providing in a flexible manner a mixture of communication, technical and research skills. Not only interns get hands-on exposure to the aforementioned skills but the organisation can make use of their deliverables.

As text-based authentication has had its critiques, non-textual techniques have been suggested throughout the last two decades. However, it is only lately, with the wide-spread adoption of smartphones and tablet devices that they have found a compelling application. Non-textual authentication may be faster and more secure and it also introduces a new paradigm for the authentication decision. We present a three factor system based on facial recognition, gesture and device ID and we define a fuzzy matching engine to handle authentication. Preliminary results indicate that such an approach can be fast and user-friendly.

A number of platforms are available to support video for eLearning purposes, yet many and diverse issues need to be addressed in order to achieve satisfactory deployment. These issues stretch from video capture to monitoring student attendance and evaluating their feedback. Albeit straightforward to address them individually, they form a chain whose weakest link determines the quality of the entire video presentation. This paper seeks to structure the process for incorporating synchronous video in eLearning, by identifying different area of concern, important goals and their associated factors and constraints. For each goal it provides a set of solutions classified in quality classes thus producing metrics for the evaluation of setting up synchronous video inside an eLearning platform.

Lately a new generation of application domains is emerging. Such applications, heavily dynamic and interactive, include interactive multimedia applications, virtual reality worlds, digital movies and 3D animations. They deal with intensive spatio-temporal dependencies between the participating objects with motion becoming a central issue.

The introduction of VRML has facilitated the production of virtual worlds. Apart from being a format for defining 3D geometries, VRML also provides the foundation for specifying interactive behaviour. However this mechanism is rather primitive, there is no direct modelling for composite events or conditions and no efficient treatment of time. The approach presented in this paper, seeks to address these issues while formalising interactive behaviour in 3D-spatiotemporal worlds. We define the 3D-STECA (3D-SpatioTemporal Event Condition Action) Rules which apply to the user and the objects of a virtual environment. The set of rules comprise a scenario which can be mapped to VRML or Java3D. With this work we document behaviour by using formal expressions and provide the basis for guaranteeing consistency in the interaction.

Composing 3D presentations is a laborious procedure partly facilitated by the introduction of VRML. VRML being a file format does not support database storage and querying of 3D objects. New presentations must be built from scratch while the objects required might already exist from previous works. In this paper we analyse a mechanism that accelerates the composition procedure by providing the functionality for storing, querying 3D objects and thus dynamically (re)constructing VRML worlds based on the user's criteria.

Introduction In many countries, people face problems regarding access to care, 24/7 support and evidence-based support. Digital interventions and services, such as chatbots, can be one option to tackle these challenges. There is a lack knowledge regarding how mental health chatbots are developed and how to ensure that there is collaboration between mental health and digital technology experts and users. Objectives This presentation describes the phases of the development for the ChatPal mental health and wellbeing chatbot. Methods Development process was conducted in five and with four different languages. First, using an electronic survey for mental health professionals (n =190) we screened how familiar they are with chatbots and how they evaluated their potential. Second, university students and staff, mental health professionals and service users (n=78) participated in workshops to design the chatbot content. Finally, the content and scripts of chatbot were written in multi-professional and multi-national collaboration. Results ChatPal is based on the PERMAH model of positive psychology and on the idea that we all have mental health which needs boosting and support from time to time. ChatPal includes relevant mental health information, exercises, mood diaries and simple monitoring and self-care tools. Based on preliminary evaluations, the ChatPal chatbot offers an option to offer support in areas where other mental health services are lacking or are insufficient. Conclusions ChatPal is already freely available in application stores and first scientific trials are have started. Preliminary results of 4-week and subsequent 12-week in-the-wild trials will be in place at the time of EPA 2022 conference. Disclosure No significant relationships.