Potential Pitfalls With Automatic Sentiment Analysis: The Example of Queerphobic Bias.

Automated sentiment analysis can help efficiently detect trends in patients' moods, consumer preferences, political attitudes and more. Unfortunately, like many natural language processing techniques, sentiment analysis can show bias against marginalised groups. We illustrate this point by showing how six popular sentiment analysis tools respond to sentences about queer identities, expanding on existing work on gender, ethnicity and disability. We find evidence of bias against several marginalised queer identities, including in the two models from Google and Amazon that seem to have been subject to superficial debiasing. We conclude with guidance on selecting a sentiment analysis tool to minimise the risk of model bias skewing results.

Design principles for conversational agents to support Emergency Management Agencies.

Widespread mis- and disinformation during the COVID-19 social media "infodemic" challenge the effective response of Emergency Management Agencies (EMAs). Conversational Agents (CAs) have the potential to amplify and distribute trustworthy information from EMAs to the general public in times of uncertainty. However, the structure and responsibilities of such EMAs are different in comparison to traditional commercial organizations. Consequently, Information Systems (IS) design approaches for CAs are not directly transferable to this different type of organization. Based on semi-structured interviews with practitioners from EMAs in Germany and Australia, twelve meta-requirements and five design principles for CAs for EMAs were developed. In contrast to the traditional view of CA design, social cues should be minimized. The study provides a basis to design robust CAs for EMAs.

Development of a smartphone virtual reality game to support the radiation therapy of children and adolescents in proton centers.

Introduction: For most patients, cancer therapy with radiation is a new experience coming with many unknown challenges. This can be stressful, particularly for children and adolescents. With the aim of reducing this stress and anxiety, a virtual-reality (VR) game, which can be used by patients prior to treatment, was developed and evaluated in a proton therapy center. Methods: The specifications were derived from literature and from interviews with medical staff and patients. The gantry including the sound of its moving components and the sound of the interlock and safety system were identified as the main features relevant for preparation of a radiation course. Potential implementation difficulties were identified in a literature study and regarded in the design. Within the VR game, patients could interact with modeled equipment of the treatment room and hear the reportedly stress-inducing sounds in a stress-free environment prior to the treatment. The VR game was evaluated in a second series of interviews with patients. Results and Discussion: This exploratory study demonstrated the specification, implementation and safe application of a VR game dedicated to young proton therapy patients. Initial anecdotal evidence suggested that the VR gaming experience was well received and found to be helpful when preparing young patients for radiation therapy.

Comparison of disclosure/concealment of medical information given to conversational agents or to physicians.

Within the anamnesis, medical information is frequently withheld, incomplete, or incorrect, potentially causing negative consequences for the patient. The use of conversational agents (CAs), computer-based systems using natural language to interact with humans, may mitigate this problem. The present research examines whether CAs differ from physicians in their ability to elicit truthful disclosure and discourage concealment of medical information. We conducted an online questionnaire with German participants (N = 148) to assess their willingness to reveal medical information. The results indicate that patients would rather disclose medical information to a physician than to a CA; there was no difference in the tendency to conceal information. This research offers a frame of reference for future research on applying CAs during the anamnesis to support physicians. From a practical view, physicians might gain better understanding of how the use of CAs can facilitate the anamnesis.

The Networked Context of COVID-19 Misinformation: Informational Homogeneity on YouTube at the Beginning of the Pandemic.

During the coronavirus disease 2019 (COVID-19) pandemic, the video-sharing platform YouTube has been serving as an essential instrument to widely distribute news related to the global public health crisis and to allow users to discuss the news with each other in the comment sections. Along with these enhanced opportunities of technology-based communication, there is an overabundance of information and, in many cases, misinformation about current events. In times of a pandemic, the spread of misinformation can have direct detrimental effects, potentially influencing citizens' behavioral decisions (e.g., to not socially distance) and putting collective health at risk. Misinformation could be especially harmful if it is distributed in isolated news cocoons that homogeneously provide misinformation in the absence of corrections or mere accurate information. The present study analyzes data gathered at the beginning of the pandemic (January-March 2020) and focuses on the network structure of YouTube videos and their comments to understand the level of informational homogeneity associated with misinformation on COVID-19 and its evolution over time. This study combined machine learning and network analytic approaches. Results indicate that nodes (either individual users or channels) that spread misinformation were usually integrated in heterogeneous discussion networks, predominantly involving content other than misinformation. This pattern remained stable over time. Findings are discussed in light of the COVID-19 "infodemic" and the fragmentation of information networks.

The influence of community structure on opinion expression: an agent-based model.

Social media has become important in shaping the public discourse on controversial topics. Many businesses therefore monitor different social media channels and try to react adequately to a potentially harmful opinion climate. Still, little is known about how opinions form in an increasingly connected world. The spiral of silence theory provides a way of explaining deviations between the perceived opinion climate and true beliefs of the public. However, the emergence of a spiral of silence on social media is hard to observe because only the thoughts of those who express their opinions are evident there. Recent research has therefore focused on modelling the processes behind the spiral of silence. A particular characteristic of social media networks is the presence of communities. Members of a community tend to be connected more with other members of the same community than with outsiders. Naturally, this might affect the development of public opinion. In the present article we investigate how the number of communities in a network and connectivity between them affects the perceived opinion climate. We find that higher connectivity between communities makes it more likely for a global spiral of silence to appear. Moreover, a network fragmented into more, smaller communities seems to provide more "safe spaces" for a minority opinion to prevail.