Personalising museum mobile guides is widely acknowledged as being important for enhancing the visitor experience. Due to the lack of information about an individual visitor and the relatively limited time of his or her visit, adapting the user interface based on a museum visitor's type is a promising approach to personalisation. This approach first requires a mechanism to identify the visitor type (‘persona’) and, second, knowledge of the preferences and needs of different types to apply personalisation. In this article, we report a face-to-face questionnaire study carried out with 105 visitors to Scitech, a science and technology visitor centre. The study aims to investigate the main facts required to identify a visitor persona and to explore the preferences of different visitor personas for particular mobile guide features. We limited our concern to the user interface features of the guide (e.g., whether it provides recommendations for related items to view) rather than what content and services the guide provides (e.g., what related items are recommended). We found that we can reliably identify the visitor persona using two multiple choice questions about visit motivation and perceived success criteria. In addition, we found that visitors have significant preferences for particular features such as presentation media, venue navigation tool, object suggestions, details level, accessing external links, exhibit information retrieval method and social interaction features such as voice communication, instant messaging, group games and challenges. Some features were found to be preferred differently by different personas such as the challenges feature, some were found to be preferred by personas differently to the overall preference such as in presentation media, and some were found to be preferred by some personas with no particular preference for others such as a venue navigation tool. Instant messaging was found to be significantly not preferred by all personas. The results provide a basis for personalisation of museum guides and services using a personas approach, which is a solution where data about individual users may be limited and where the individual configuration of a user interface may not be practical or warranted.

The Conlan whitepaper makes a compelling case for a community-scale means of evaluating algorithms for user modeling, adaptation and personalisation (UMAP). The authors propose an evaluation paradigm focused on a personalisation use case within an open modeling environment. Their use case is one where a mobile interface learns a user's preferences for different notifications in different contexts. Additional use cases could be incorporated in this paradigm to provide contrasting kinds of challenge for personalisation evaluation. In this position paper we summarise a use case where personalisation is achieved by categorising a user and switching their interface to a variant. The user interface is a mobile news app within a platform that also comprises a user modeling function and an interface personalisation service. Comparison of the use cases helps to map the space for the evaluation paradigm.

It is widely agreed that museums and other cultural heritage venues should provide visitors with personalised interaction and services such as personalised mobile guides, although currently most do not. Since museum visitors are typically first-time visitors and since their visit is for a relatively short session, personalisation should use initial interaction data to associate the user with a particular persona and thereby infer other facts about the user's preferences and needs. In this paper we report a questionnaire-based study carried out with 105 visitors of a Science and Technology Centre to examine the minimal features needed to identify visitor personas. We find that museum visitors can be clustered by their visit motivation and perceived success factors; these clusters are found to correspond both with Falk's visitor categorisation and a prior classification of exploration styles. Consequently, these two features can be used to reliably identify the visitor persona, and therefore, can be used for user modeling.

The way people read digital news - as distinct from what news they read - has emerged as a significant concern for research in user modelling and personalisation. Intuitively, some people read the news frequently and broadly whilst others read it occasionally and selectively. It is likely that these differences in news reading behaviour arise in part from differences in peoples' personalities. We report a study that surveyed the digital news reading habits and personality traits of 241 people. We find correlations between most news reading characteristics (e.g., how much time over a day a person reads news) and some personality traits (e.g Openness-toExperience). The correlations provide a better understanding of the different types of news reading user and why they read news in different ways. They indicate the value of extending user model profiles to include personality traits along with domain specific activity factors.

Meetings frequently involve discussion of documents and can be significantly affected if a document is absent. An agent system capable of spontaneously retrieving a document at the point it is needed would have to judge whether a meeting is talking about a particular document and whether that document is already present. We report the exploratory application of agent techniques for making these two judgements. To obtain examples from which an agent system can learn, we first conducted a study of participants making these judgements with video recordings of meetings. We then show that interactions between hands and paper documents in meetings can be used to recognise when a document being talked about is not to hand. The work demonstrates the potential for multimodal agent systems using these techniques to learn to perform specific, discourse-level tasks during meetings.

The news you read is, of course, a highly individual choice and one for which substantial and successful news recommendation techniques have been developed. But as well as what news you read, the way you choose and read that news is also known to be highly individual. We propose a framework for extending the user profile of news readers with features of these interactions. The extensions are dynamic through monitoring an individual's reading and browsing activity. They include factors learned from the user's interaction log and also factors inferred from category level definitions contained in the framework. We report a study in which users' interaction logs with a news app are used to generate user profiles that are verified with self-reported questionnaire data about reading habits. We discuss the implications of our user modeling approach in news personalisation for both recommendation and user interface personalisation for news apps.

Digital museum guides promise a transformed visitor experience through greater engagement with the museum content and activities. Realising that promise turns on the personalisation of digital guides, particularly in museum contexts where rich content is accessed by a highly diverse visitor population. Since users of a museum guide are typically first time users and since their usage is for a relatively short session, personalisation must use initial interaction data to associate the user with a particular persona and thereby infer other facts about the user’s preferences and needs. Two research aims follow: first to better understand the requirements of different visitor personas, and second, to develop methods for unobtrusively detecting a user’s persona from their interactions with a guide and their activity in the museum space. This paper presents the design of a research programme for: first, investigating mechanisms for automatic adaptation of digital museum guides based on identifying a visitor’s persona category from interaction data; second, exploring the requirements of different visitor categories to derive the user interface adaptation, and; third, investigating the effectiveness of this adaptation on the museum visitor’s experience.

Television companion apps on tablets and smartphones provide interactive content synchronized with TV shows. A key design question raised by this novel, multi-display, multimedia interface is whether the app's role is to be a synopsis of the show or a supplement. In other words, should the app help viewers better follow what they are watching on TV, or offer additional enriching content to respond to interest created by the show? We developed a companion app for a documentary with both synoptic and supplementary content. A laboratory study with 28 participants examined the effect of these different types of content on the experience of using the companion and the effect on engagement with the show in terms of participants' recall. Engagement with the show was not affected by supplementary content in the app but coordinated viewing of both screens was more difficult. Design guidelines evident from these results are discussed.

News is increasingly being accessed on smartphones and tablets, establishing mobile news reading as one of the most popular activities on mobile devices. News reading is also a very individual activity with marked differences in the way people read and access the news, however, news apps have limited personalization. In this paper, we approach news personalization as a two-dimensional problem. We discuss news personalization in terms of 'what' content is delivered to the user and 'how' that content is consumed. We present our approach towards user interface personalization in news apps and we conclude that news content recommendation and user interface personalization should co-exist in news apps.

Operators of dynamic systems often use time-series data to support their diagnostic and proactive decision-making. Those data have traditionally been displayed in the form of separate trend charts, for example, line graphs of pressure and temperature over time. Configural object displays are a widely advocated approach to the visual integration of information yet have been applied only rarely to time-series data. One example was the 'time tunnel' format but its benefits were equivocal, seemingly compromised by its graphical complexity. There is then the need to investigate other graphical forms for object displays of time series data. This research will require a microworld representing a knowledge-rich task domain accessible to multiple participants (the nuclear power plant simulation used with the time tunnel display studies required participants to have 20 hours of experience with the system). We report a design for such a microworld that adopts the domain of financial control of a business where decisions need to be made about the pricing of products to optimize returns in a changing and sometimes volatile market. Alternative visual displays of the essential time series data for this domain are possible and whilst decision making is knowledge rich, involving reasoning about high level relationships, pilot tests showed that it is accessible to participants with only moderate training.

This demonstration paper accompanies a paper accepted at MobileHCI'15 [1]. With the aim of enhancing news reading experience on smartphones, we developed and deployed Habito News, a dedicated Android news app capable of unobtrusive logging of news interactions and recognising patterns of user's news reading behaviour. Interaction traces collected with Habito News can first be used to detect the user's news reader type and then to adapt the news reading app displays and behavior in response to individual patterns of user's interaction. In this demo, we present the app's logging capabilities, the automatic detection of news reader types and the three different user interface designs for different news reader types.

Smartphones are capable of alerting their users to different kinds of digital interruption using different modalities and with varying modulation. Smart notification is the capability of a smartphone for selecting the user's preferred kind of alert in particular situations using the full vocabulary of notification modalities and modulations. It therefore goes well beyond attempts to predict if or when to silence a ringing phone call. We demonstrate smart notification for messages received from a document retrieval system while the user is attending a meeting. The notification manager learns about their notification preferences from users' judgements about videos of meetings. It takes account of the relevance of the interruption to the meeting, whether the user is busy and the sensed location of the smartphone. Through repeated training, the notification manager learns to reliably predict the preferred notification modes for users and this learning continues to improve with use.

The use of a companion app to augment viewing of information-rich television programmes is investigated. The app displays a synchronised graphical abstraction of a programme’s content in the form of a concept map. Two experiments were conducted involving participants watching an astronomy documentary with the app. The first compared watching the programme with and without the app, and the second compared non-interactive and interactive versions of the app. Understanding of the programme, cross-device gaze behaviour, and user experience of the app were assessed. Our results show that the companion app improved participants’ understanding and recall of the programme. Participants were found to manage their visual attention systematically when using the companion app, and correlations were found in the way they shifted their gaze from TV screen to tablet and back in response to changes in the programme content. Increasing interaction with the app disrupted understanding of the television programme and visual attention. Participants were positive about the value of companion apps for understanding and recall of programmes, but distraction and ‘knowing where to look’ were significant concerns.

Companion apps for television programmes provide additional, synchronized and interactive content on mobile devices such as tablets or smartphones. With the television screen they create dual screen interfaces with multiple modalities and require viewers to actively manage their visual attention. We outline a model of interactions with companion apps used with information-rich television programmes where a primary purpose the app is to support understanding and learning. Our model summarises perceptual and cognitive processes involved by drawing on theories and findings from Human Factors and the learning sciences. We use the model to assess CompanionMap, an app for accompanying science documentaries with synchronized, animated concept maps. We show how the model provides explanations for four key results obtained from an experiment with CompanionMap, including how users managed their visual attention and how they learnt about astrophysics when using the app to watch an astronomy programme.

This demonstration paper accompanies a paper accepted at MobileHCI'15 [1]. With the aim of enhancing news reading experience on smartphones, we developed and deployed Habito News, a dedicated Android news app capable of unobtrusive logging of news interactions and recognising patterns of user's news reading behaviour. Interaction traces collected with Habito News can first be used to detect the user's news reader type and then to adapt the news reading app displays and behavior in response to individual patterns of user's interaction. In this demo, we present the app's logging capabilities, the automatic detection of news reader types and the three different user interface designs for different news reader types.

As news is increasingly accessed on smartphones and tablets, the need for personalising news app interactions is apparent. We report a series of three studies addressing key issues in the development of adaptive news app interfaces. We first surveyed users' news reading preferences and behaviours; analysis revealed three primary types of reader. We then implemented and deployed an Android news app that logs users' interactions with the app. We used the logs to train a classifier and showed that it is able to reliably recognise a user according to their reader type. Finally we evaluated alternative, adaptive user interfaces for each reader type. The evaluation demonstrates the differential benefit of the adaptation for different users of the news app and the feasibility of adaptive interfaces for news apps.

This research presents the concept of a non-command interface for a smart room to automatically detect when people talk about a document and whether it is present or not, as a fundamental prerequisite for missing document provision that doesn't require explicit requests, avoiding distraction from the main discourse. A study on how observers judge document usage in meetings is presented as a baseline and the conceptual framework is briefly explained. Finally, an exploratory experiment is reported. These elements demonstrate the research feasibility and define the techniques needed to build the agent.