Frans van der Sluis

When complexity becomes interesting

How to provide users a positive experience during interaction with information (i.e., the “Information eXperience” (IX)) is still an open question. As a starting point, this work investigates how the emotion of interest can be influenced by modifying the complexity of the information presented to users. The appraisal theory of interest suggests a “sweet spot” where interest will be at its peak: information that is novel and complex yet still comprehensible. This “sweet spot” is approximated using two studies. Study One develops a computational model of textual complexity founded on psycholinguistic theory on processing difficulty. The model was trained and tested on 12,420 articles, achieving a classification performance of 90.87% on two classes of complexity. Study Two puts the model to its ultimate test: Its application to change the users IX. Using 18 news articles the influence of complexity on interest and its appraisals is unveiled. A structural equation model shows a positive influence of complexity on interest, yet a negative influence of comprehensibility, confirming a seemingly paradoxical relationship between complexity and interest. By showing when complexity becomes interesting, this paper shows how information systems can use the model of textual complexity to construct an interesting IX.

EmSe: initial evaluation of a child-friendly medical search system

When undergoing medical treatment in combination with extended stays in hospitals, children have been frequently found to develop an interest in their condition and the course of treatment. A natural means of searching for related information would be to use a web search engine. The medical domain, however, imposes several key challenges on young and inexperienced searchers, such as difficult terminology, potentially frightening topics or non-objective information offered by lobbyists or pharmaceutical companies. To address these problems, we present the design and usability study of EmSe, a search service for children in a hospital environment.

Information Retrieval eXperience (IRX): Towards a Human-Centered Personalized Model of Relevance

We approach Information Retrieval (IR) from a User eXperience (UX) perspective. Through introducing a model for Information Retrieval eXperience (IRX), this paper operationalizes a perspective on IR that reaches beyond topicality. Based on a documents topicality, complexity, and emotional value, a model of relevance is proposed to influence users IRX and, consequently, the synthesis and use of the retrieved information. Additionally, methods are discussed to assess UX through interaction and feedback mechanisms. As such, the proposed multi-dimensional IRX model is highly user-dependent and determines documents relevance from a non-traditional human-centered, personalized perspective on IR.

Telling the story and re-living the past: How speech analysis can reveal emotions in post-traumatic stress disorder (PTSD) patients

A post-traumatic stress disorder (PTSD) is a severe stress disorder and, as such, a severe handicap in daily life. To this date, its treatment is still a big endeavor for therapists. This chapter discusses an exploration towards automatic assistance in treating patients suffering from PTSD. Such assistance should enable objective and unobtrusive stress measurement, provide decision support on whether or not the level of stress is excessive, and, consequently, be able to aid in its treatment. Speech was chosen as an objective, unobtrusive stress indicator, considering that most therapy sessions are already recorded anyway. Two studies were conducted: a (controlled) stress-provoking story telling (SPS) and a(n ecologically valid) re-living (RL) study, each consisting of a “happy” and an “anxiety triggering” session. In both studies the same 25 PTSD patients participated. The Subjective Unit of Distress (SUD) was determined as a subjective measure, which enabled the validation of derived speech features. For both studies, a Linear Regression Model (LRM) was developed, founded on patients’ average acoustic profile. It used five speech features: amplitude, zero crossings, power, high-frequency power, and pitch. From each feature, 13 parameters were derived; hence, in total 65 parameters were calculated. Using LRMs, respectively 83 and 69% of the variance was explained for the SPS and RL study. Moreover, a set of generic speech signal parameters was presented. Together, the models created and parameters identified can serve as the foundation for future artificial therapy assistants.

Using complexity measures in information retrieval

Although IR is meant to serve its users, surprisingly little IR research is not user-centered. In contrast, this article utilizes the concept complexity of information as the determinant of the users comprehension, not as a formal golden measure. Four aspects of users comprehension are applies on a database of simple and normal Wikipedia articles and found to distinguish between them. The results underline the feasibility of the principle of parsimony for IR: where two topical articles are available, the simpler one is preferred.

Therapy progress indicator (TPI): Combining speech parameters and the subjective unit of distress

A posttraumatic stress disorder (PTSD) is a severe handicap in daily life and its treatment is complex. To evaluate the success of treatments, an objective and unobtrusive expert system was envisioned: an therapy progress indicator (TPI). Speech was considered as an excellent candidate for providing an objective, unobtrusive emotion measure. Speech of 26 PTSD patients was recorded while they participated in two reliving sessions: re-experiencing their last panic attack and their last joyful occasion. As a subjective measure, the subjective unit of distress was determined, which enabled the validation of derived speech features. A set of parameters of the speech features: signal, power, zero crossing ratio, and pitch, was found to discriminate between the two sessions. A regression model involving these parameters was able to distinguish between positive and negative distress. This model lays the foundation for an TPI for patients with PTSD, which enables objective and unobtrusive evaluations of therapies.

Visual exploration of health information for children

Children experience several difficulties retrieving information using current Information Retrieval (IR) systems. Particularly, children struggle to find the right keywords to construct queries given their lack of domain knowledge. This problem is even more critical in the case of the specialized health domain. In this work we present a novel method to address this problem using a cross-media search interface in which the textual data is searched through visual images. This solution aims to solve the recall and recognition problem which is salient for health information, by replacing the need for a vocabulary with the easy task of recognising the different body parts.

Designing a Museum Multi-Touch Table for Children

Tangible user interfaces allow children to take advantage of their experience in the real world with multimodal human interactions when interacting with digital information. In this paper we describe a model for tangible user interfaces that focuses mainly on the user experience during interaction. This model is related to other models and used to design a multitouch tabletop application for a museum. We report about our first experiences with this museum application.

Bombs, fish, and coral reefs

Often, the way subject matter is included in educational games does not fully utilize or sometimes even inhibits the full learning potential of games. This paper argues that in order to optimally use the potential of games for learning, games should be endogenous. An endogenous educational game is a game where the educational content is integrated in the game play mechanics themselves, rather than bolted-on using explicit messages. This research examines the relation between explicit messages, explorative game behavior, and comprehension by developing two versions of an endogenous educational game about overfishing, one with and one without an explicit purpose. The game was tested with 13 children aged 8 to 11. The results indicate that factual knowledge and comprehension is increased with explicit messages, and in particular deep comprehension is fostered by explorative game behavior. This confirms the plea for endogenous games to teach about bombs, fish, coral reefs, and more.

Making the news interesting: understanding the relationship between familiarity and interest

News feeds are an important element of information encountering, feeding our (new) interests but also leading to a state of information overload. Current solutions often select information similar to the users interests. However, long-term interest in one topic, and being highly familiar with that topic, does not necessarily imply an actual interest response will occur when more of the same topic is selected. This study explores how important familiarity is in predicting an interest response. In a study with 30 subjects, interest was manipulated by topical familiarity using novel stimuli from a popular news source. This study shows, within this context, familiarity is moderately important for an interest response: familiarity does indeed make the news interesting, but only to a certain extent. The results set a baseline for predicting interest during information encountering, indicating familiarity is important, but not the only influential variable a system should consider when selecting information for users.