Exploring Issues of User Model Transparency and Proactive Behaviour in an Office Environment Control System

It is important that systems that exhibit proactive behaviour do so in a way that does not surprise or frustrate the user. Consequently, it is desirable for such systems to be both personalised and designed in such a way as to enable the user to scrutinise her user model (part of which should hold the rules describing the behaviour of the system). This article describes on-going work to investigate the design of a prototype system that can learn a given user’s behaviour in an office environment in order to use the inferred rules to populate a user model and support appropriate proactive behaviour (e.g. turning on the user’s fan under appropriate conditions). We explore the tension between user control and proactive services and consider issues related to the design of appropriate transparency with a view to supporting user comprehensibility of system behaviour. To this end, our system enables the user to scrutinise and possibly over-ride the ‘IF-THEN’ rules held in her user model. The system infers these rules from the context history (effectively a data set generated using a variety of sensors) associated with the user by using a fuzzy-decision-tree-based algorithm that can provide a confidence level for each rule in the user model. The evolution of the system has been guided by feedback from a number of real-life users in a university department. A questionnaire study has yielded supplementary results concerning the extent to which the approach taken meets users’ expectations and requirements.     

Study of collective user behaviour in Twitter: a fuzzy approach

The study of collective user behaviours in social networking sites has become an increasing important topic in social media mining. Understanding such behaviours has its potential to extract actionable patterns that can be beneficial to develop effective marketing strategies, optimise user experiences and maximise website revenues. With the rapid development of micro-blogging, Twitter has become a richer source of intelligence that can be used to study collective user behaviour, due to its efficient and meaningful user-to-user interactions. However, the classical statistical methods have some drawbacks in bridging the gap between user-generated data and human analysts who mostly use linguistic terms to analyse data and model/summarise knowledge learned. To address this gap, this work proposes a new approach, which employs the mass assignment theory-based fuzzy association rules algorithm (MASS-FARM), for the first time, to extract useful interaction behaviour of Twitter users. The influential factors (including activity time, number of friends/followers and the number of tweets) are represented as fuzzy granules, and the associations amongst are studied by employing MASS-FARM. The collective user behaviours are analysed in the Reply category and the Non-Reply category, respectively. The applicability and usefulness of the proposed method are demonstrated via an empirical study on a collected Twitter data set. The derived results are also discussed and compared with existing works.     

Assisted Navigation for Persons with Reduced Mobility: Path Recognition Through Particle Filtering (Condensation Algorithm)

In the few past decades, several international researchers have worked to develop intelligent wheelchairs for the people with reduced mobility. For many of these projects, the structured set of commands is based on a sensor-based command. Many types of commands are available but the final decision is to be made by the user. A former work established a behaviour-based multi-agent form of control ensuring that the user selects the best option for him/her in relation to his/her preferences or requirements. This type of command aims at “merging” this user and his/her machine—a kind of symbiotic relationship making the machine more amenable and the command more effective. In this contribution, the approach is based on a curve matching procedure to provide comprehensive assistance to the user. This new agent, using a modelization of the paths that are most frequently used, assists the user during navigation by proposing the direction to be taken when the path has been recognized. This approach will spare the user the effort of determining a new direction—which might be a major benefit in the case of severe disabilities. The approach considered uses particle filtering to implement the recognition of the most frequent paths according to a topological map of the environment.     

Toward a Multidisciplinary Model of Context to Support Context-Aware Computing

Capturing, defining, and modeling the essence of context are challenging, compelling, and prominent issues for interdisciplinary research and discussion. The roots of its emergence lie in the inconsistencies and ambivalent definitions across and within different research specializations (e.g., philosophy, psychology, pragmatics, linguistics, computer science, and artificial intelligence). Within the area of computer science, the advent of mobile context-aware computing has stimulated broad and contrasting interpretations due to the shift from traditional static desktop computing to heterogeneous mobile environments. This transition poses many challenging, complex, and largely unanswered research issues relating to contextual interactions and usability. To address those issues, many researchers strongly encourage a multidisciplinary approach. The primary aim of this article is to review and unify theories of context within linguistics, computer science, and psychology. Summary models within each discipline are used to propose an outline and detailed multidisciplinary model of context involving (a) the differentiation of focal and contextual aspects of the user and application's world, (b) the separation of meaningful and incidental dimensions, and (c) important user and application processes. The models provide an important foundation in which complex mobile scenarios can be conceptualized and key human and social issues can be identified. The models were then applied to different applications of context-aware computing involving user communities and mobile tourist guides. The authors' future work involves developing a user-centered multidisciplinary design framework (based on their proposed models). This will be used to design a large-scale user study investigating the usability issues of a context-aware mobile computing navigation aid for visually impaired people.     

Analysis and Classification of Human Driving Behaviour in an Urban Environment*

Intelligent vehicle systems have introduced the need for designers to consider user preferences so as to make several kinds of driving features as driver friendly as possible. This requirement raises the problem of how to suitably analyse human performance so they can be implemented in automatic driving tasks. The framework of the present work is an adaptive cruise control with stop and go features for use in an urban setting. In such a context, one of the main requirements is to be able to tune the control strategy to the driver’s style. In order to do this, a number of different drivers were studied through the statistical analysis of their behaviour while driving. The aim of this analysis is to decide whether it is possible to determine a driver’s behaviour, what signals are suitable for this task and which parameters can be used to describe a driver’s style. An assignment procedure is then introduced in order to classify a driver’s behaviour within the stop and go task being considered. Finally, the findings were analysed subjectively and compared with a statistically objective one.     

An ambient software monitoring system for unsupervised user modelling

This paper describes a means of unsupervised learning of recurring patterns in user activity through patterns in system level events generated by a graphical user interface. Earlier work has shown that using this distillation of the more complex behavioural interaction between the user and the application provides a symbolic representation of knowledge and goals that could be used to imply preference. Although prior research has explored the possibilities of removing this information acquisition bottleneck in such an expert system using ambient monitoring approaches, some have experienced difficulty in dealing with the varying length training sequences and segmentation of the continuous event stream. Unlike previous work the approach documented here handles interactions of varying sizes and is able to recall recurrent patterns in real time irrespective of the number of interactions learned. In addition to describing the proposed approach we also describe the shortcomings of various previously applied machine learning techniques on the same type of data. We also demonstrate a practical implementation of our approach applied to web browser usage.     

Aspects of availability: Enforcing timed properties to prevent denial of service

We propose a domain-specific aspect language to prevent denial of service caused by resource management. Our aspects specify availability policies by enforcing time limits in the allocation of resources. In our language, aspects can be seen as formal timed properties on execution traces. Programs and aspects are specified as timed automata and the weaving process as an automata product. The benefit of this formal approach is two-fold: the user keeps the semantic impact of weaving under control and (s)he can use a model-checker to optimize the woven program and verify availability properties. This article presents the main approach (programs, aspects, weaving) formally using timed safety automata. The specification of resources, optimizations and verification are sketched in a more intuitive fashion. Even if a concrete implementation remains as future work, we address some high-level implementation issues and illustrate the approach by small examples and a case study.     

Modeling and detecting semantic-based interactions in aspect-oriented scenarios

Interactions between dependent or conflicting aspects are a well-known problem with aspect-oriented development (as well as related paradigms). These interactions are potentially dangerous and can lead to unexpected or incorrect results when aspects are composed. To date, the majority of aspect interaction detection methods either have been based on purely syntactic comparisons or have relied on heavyweight formal methods. We present a new approach that is based instead on lightweight semantic annotations of aspects. Each aspect is annotated with domain-specific markers and a separate influence model describes how semantic markers from different domains influence each other. Automated analysis can then be used both to highlight semantic aspect conflicts and to trade-off aspects. We apply this technique to early aspects, namely, aspect scenarios, because it is desirable to detect aspect interactions as early in the software lifecycle as possible. We evaluate the technique using two case studies—one from industry and one posed as a challenge problem by the community—and show that the technique detects interactions that cannot be discovered using syntactic techniques. In addition, we show that the technique can apply to many languages through the use of different aspect-oriented scenario notations in the case studies, namely, MATA sequence diagrams and Aspect-oriented Use Case Maps.     

Is simplicity the key to engagement for children on the autism spectrum?

This article presents a conceptualisation of technologies as simple, ambient forms. By avoiding the tendency to solve problems and by being open to interaction that emerges through repetition and flow, we argue that technology can offer more for people than functionality. When the user is given freedom to discover control without burdensome cognitive demands and the fear of failure, even everyday technologies can arouse curiosity and thus reveal untapped ability. What is unique about our work is its therapeutic application as a medium for engaging the most hard to reach children on the autism spectrum. Our theoretical foundations are drawn from the human–computer interaction paradigm of tangible interaction. This is of interest to us as a framework for the study of the physical and sensory manipulation of information. For children with cognitive and developmental delays, discovering a close match between physical control and digital response has proved both rewarding and motivating. The significance of this is illustrated through a range of studies undertaken with children with autism spectrum disorders. These include a mixed group attending a holiday club, a study that introduced keyboard activities to children with poor receptive communication and a case study using an ordinary microphone. The research captures emergent, exploratory interaction with a software application called ReacTickles. The case study uses a specifically customised video coding technique to analyse idiosyncratic interactions that demonstrate the impact of simple, playful interaction on self-esteem and creativity.     

Data-driven models for timing feedback responses in a Map Task dialogue system

Traditional dialogue systems use a fixed silence threshold to detect the end of users’ turns. Such a simplistic model can result in system behaviour that is both interruptive and unresponsive, which in turn affects user experience. Various studies have observed that human interlocutors take cues from speaker behaviour, such as prosody, syntax, and gestures, to coordinate smooth exchange of speaking turns. However, little effort has been made towards implementing these models in dialogue systems and verifying how well they model the turn-taking behaviour in human–computer interactions. We present a data-driven approach to building models for online detection of suitable feedback response locations in the user's speech. We first collected human–computer interaction data using a spoken dialogue system that can perform the Map Task with users (albeit using a trick). On this data, we trained various models that use automatically extractable prosodic, contextual and lexico-syntactic features for detecting response locations. Next, we implemented a trained model in the same dialogue system and evaluated it in interactions with users. The subjective and objective measures from the user evaluation confirm that a model trained on speaker behavioural cues offers both smoother turn-transitions and more responsive system behaviour.     

User diversity and design representation: Towards increased effectiveness in Design for All

This paper addresses user modelling for “Design for All” in a model-based approach to Human-Computer Interaction, paying particular attention to placing user models within organisational role- and task-related contexts. After reviewing a variety of user modelling approaches, and deriving requirements for user modelling related to Design for All, the paper proposes a role-driven individualised approach. Such an approach is based on a model-based representation schema and a unifying notation that keeps the user’s models and the contextual information transparent and consistent. Individualisation is achieved by coupling symbolic model specifications with neural networking on synchronisation links between symbolic representation elements. As a result, user modelling for Design for All is achieved not by stereotypical user properties and functional roles, but by accommodating the actual users’ behaviour. Published online: 18 May 2001     

Modeling the behavior of users who are confronted with security mechanisms

In this paper, we describe a new approach to analyze the trade-off between usability and security frequently found in security-related user interfaces. The approach involves the simulation of potential user interaction behavior by a mixed probabilistic and rule-driven state machine. On the basis of the simulations, user behavior in security-relevant situations can be predicted and user interfaces optimizing intended behavior can be designed. The approach is evaluated in an artificial microworld setting which provides good control over the experimental factors guiding the behavior. A comparison of empirical and simulated behavior in this microworld shows that the approach is already able to accurately predict important aspects of user behavior toward security interfaces, but also identifies future work necessary to better cover all relevant aspects guiding this behavior in a real-world setting.     

Control centric approach in designing scrolling and zooming user interfaces

The dynamic systems approach to the design of continuous interaction interfaces allows the designer to use simulations, and analytical tools to analyse the behaviour and stability of the controlled system alone and when it is coupled with a manual control model of user behaviour. This approach also helps designers to calibrate and tune the parameters of the system before the actual implementation, and in response to user feedback. In this work we provide a dynamic systems interpretation of the coupling of internal states involved in speed-dependent automatic zooming, and test our implementation on a text browser on a Pocket PC instrumented with a tilt sensor. We illustrate simulated and experimental results of the use of the proposed coupled navigation and zooming interface using tilt and touch screen input.     

On the relation between cognitive and biological modelling of criminal behaviour

This article discusses how a cognitive modelling approach for criminal behaviour can be related to a biological modelling approach. The discussion is illustrated by a case study for the behaviour of three types of violent criminals as known from literature within the area of Criminology. A cognitive model is discussed that can show each of the behaviours of these types of criminals, depending on the characteristics set and inputs in terms of stimuli from the environment. Based on literature in Criminology about motivations and opportunities and their underlying biological factors, it is shown by a formal interpretation mapping how the model can be related to a biological grounding. This formal mapping covers ontology elements for states and dynamic properties for processes, and thus shows how the cognitive model can be biologically grounded.     

Agency modulates interactions with automation technologies

The increasing presence of automation between operators and automated systems tends to disrupt operators from action outcomes, leading them to leave the control loop. The theoretical framework of agency suggests that priming the operator about the system’s upcoming behaviour could help restore an appropriate sense of control and increase user acceptance of what the system is doing. In a series of two experiments, we test whether providing information about what the system is about to do next leads to an increase in the level of user acceptance, concomitant with an increase in control and performance. Using an aircraft supervision task, we demonstrated the benefit of prime messages regarding system acceptance and performance. Taken together, our results indicate that the principles proposed by this framework could be used to improve human–machine interaction and maintain a high level of sense of control in supervisory tasks.

Practitioner Summary: The out-of-the-loop performance problem is a major potential consequence of automation, leaving operators helpless to takeover automation in case of failure. Using an aircraft supervision task, the following article illustrates how the psychological approach of agency can help improving human–system interactions by designing more acceptable and more controllable automated interfaces     

Computers that recognise and respond to user emotion: theoretical and practical implications

Prototypes of interactive computer systems have been built that can begin to detect and label aspects of human emotional expression, and that respond to users experiencing frustration and other negative emotions with emotionally supportive interactions, demonstrating components of human skills such as active listening, empathy, and sympathy. These working systems support the prediction that a computer can begin to undo some of the negative feelings it causes by helping a user manage his or her emotional state. This paper clarifies the philosophy of this new approach to human–computer interaction: deliberately recognising and responding to an individual user's emotions in ways, that help users meet their needs. We define user needs in a broader perspective than has been hitherto discussed in the HCI community, to include emotional and social needs, and examine technology's emerging capability to address and support such needs. We raise and discuss potential concerns and objections regarding this technology, and describe several opportunities for future work.     

Information fusion in practice: A distributed cognition perspective on the active role of users

Traditionally, the focus of most information fusion research has been on computational aspects, as illustrated by, for example, different versions of the JDL data fusion model. Consequently, the human user has mainly been conceived as a relatively passive recipient of fused information. However, the importance of understanding the active role of human information processing in information fusion is gaining increasing recognition, as also reflected in discussions of a ”level 5” in the JDL model. This paper presents a case study of the interaction between human and machine information processing in a maritime surveillance control room. A detailed analysis of cognitive processes and information flows involved in identifying and tracking moving vessels illustrates how machines and human operators collaboratively perform fusion in a highly distributed fashion. The theoretical framework of distributed cognition provides an alternative or complementary way of analysing information fusion systems/processes that more clearly reveals the actual complexities of the interaction between human and machine information processing in practice.