Showing papers by "Helsinki Institute for Information Technology published in 2004"

Metadata creation system for mobile images

Abstract: The amount of personal digital media is increasing, and managing it has become a pressing problem. Effective management of media content is not possible without content-related metadata. In this paper we describe a content metadata creation process for images taken with a mobile phone. The design goals were to automate the creation of image content metadata by leveraging automatically available contextual metadata on the mobile phone, to use similarity processing algorithms for reusing shared metadata and images on a remote server, and to interact with the mobile phone user during image capture to confirm and augment the system supplied metadata. We built a prototype system to evaluate the designed metadata creation process. The main findings were that the creation process could be implemented with current technology and it facilitated the creation of semantic metadata at the time of image capture.

From context to content: leveraging context to infer media metadata

Abstract: The recent popularity of mobile camera phones allows for new opportunities to gather important metadata at the point of capture. This paper describes a method for generating metadata for photos using spatial, temporal, and social context. We describe a system we implemented for inferring location information for pictures taken with camera phones and its performance evaluation. We propose that leveraging contextual metadata at the point of capture can address the problems of the semantic and sensory gaps. In particular, combining and sharing spatial, temporal, and social contextual metadata from a given user and across users allows us to make inferences about media content.

Applying discrete PCA in data analysis

Abstract: Methods for analysis of principal components in discrete data have existed for some time under various names such as grade of membership modelling, probabilistic latent semantic analysis, and genotype inference with admixture. In this paper we explore a number of extensions to the common theory, and present some application of these methods to some common statistical tasks. We show that these methods can be interpreted as a discrete version of ICA. We develop a hierarchical version yielding components at different levels of detail, and additional techniques for Gibbs sampling. We compare the algorithms on a text prediction task using support vector machines, and to information retrieval.

Long-term working memory and interrupting messages in human-computer interaction

Abstract: The extent to which memory for information content is reliable, trustworthy, and accurate is crucial in the information age. Being forced to divert attention to interrupting messages is common, however, and can cause memory loss. The memory effects of interrupting messages were investigated in three experiments. In Experiment 1, attending to an interrupting message decreased memory accuracy. Experiment 2, where four interrupting messages were used, replicated this result. In Experiment 3, an interrupting message was shown to be most disturbing when it was semantically very close to the main message. Drawing from a theory of long-term working memory it is argued that interrupting messages can both disrupt the active semantic elaboration of content during encoding and cause semantic interference upon retrieval. Properties of the interrupting message affect the extent and type of errors in remembering. Design implications are discussed.

A three-way merge for XML documents

Abstract: Three-way merging is a technique that may be employed for reintegrating changes to a document in cases where multiple independently modified copies have been made. While tools for three-way merge of ASCII text files exist in the form of the ubiquitous diff and patch tools these are of limited applicability to XML documents.We present a method for three-way merging of XML which is targeted at merging XML formats that model human-authored documents as ordered trees (e.g. rich text formats structured text drawings etc.). To this end we investigate a number of use cases on XML merging (collaborative editing propagating changes across document variants) from which we derive a set of high-level merge rules. Our merge is based on these rules.We propose that our merge is easy to both understand and implement yet sufficiently expressive to handle several important cases of merging on document structure that are beyond the capabilities of traditional text-based tools. In order to justify these claims we applied our merging method to the merging tasks contained in the use cases. The overall performance of the merge was found to be satisfactory.The key contributions of this work are: a set of merge rules derived from use cases on XML merging a compact and versatile XML merge in accordance with these rules and a classification of conflicts in the context of that merge.

Photo annotation on a camera phone

Abstract: In this paper we describe a system that allows users to annotate digital photos at the time of capture. The system uses camera phones with a lightweight client application and a server to store the images and metadata and assists the user in annotation on the camera phone by providing guesses about the location and content of the photos. By conducting user interface testing, surveys, and focus groups we were able to evaluate the usability of this system and uncover usage patterns and motivations that will inform our development of future mobile media annotation applications. In this paper we present usability issues encountered in using a camera phone as an image annotation device immediately after image capture and users' responses to use of such a system.

MobShare: controlled and immediate sharing of mobile images

Abstract: In this paper we describe the design and implementation of a mobile one picture sharing system MobShare that enables immediate, controlled, and organized sharing of mobile pictures, and the browsing, combining, and discussion of the shared pictures. The design combines research on otogray, personal image management, mobile one camera use, mobile picture publishing, and an interview study we conducted on mobile one camera users. The system is based on a client-server architecture and uses current mobile one and web technology. The implementation describes novel solutions in immediate sharing of mobile images to an organized web album, and in providing full control over with whom the images are shared. Also, we describe new ways of promoting discussion in sharing images and enabling the combination and comparison of personal and shared pictures. The system proves that the designed solutions can be implemented with current technology and provides novel approaches to general issues in sharing digital images.

Relational link-based ranking

Abstract: Link analysis methods show that the interconnections between web pages have lots of valuable information. The link analysis methods are, however, inherently oriented towards analyzing binary relations. We consider the question of generalizing link analysis methods for analyzing relational databases. To this aim, we provide a generalized ranking framework and address its practical implications. More specically, we associate with each relational database and set of queries a unique weighted directed graph, which we call the database graph. We explore the properties of database graphs. In analogy to link analysis algorithms, which use the Web graph to rank web pages, we use the database graph to rank partial tuples. In this way we can, e.g., extend the PageRank link analysis algorithm to relational databases and give this extension a random querier interpretation. Similarly, we extend the HITS link analysis algorithm to relational databases. We conclude with some preliminary experimental results.

Combining Topic Models and Social Networks for Chat Data Mining

Abstract: Informal chat-room conversations have intrinsically different properties from regular static document collections. Noise, concise expressions and dynamic, changing and interleaving nature of discussions make chat data ill-suited for analysis with an off-the-shelf text mining method. On the other hand, interactive human communication has some implicit features which may be used to enhance the results. In our research we infer social network structures from the chat data by using a few basic heuristics. We then present some preliminary results showing that the inferred social graph may be used to enhance topic identification of a chat room when combined with a state-of-the-art topic and classification models. For validation purposes we then compare the performance effects of using this social information in a topic classification task.

Geometric and combinatorial tiles in 0-1 data

Abstract: In this paper we introduce a simple probabilistic model, hierarchical tiles, for 0-1 data. A basic tile (X,Y,p) specifies a subset X of the rows and a subset Y of the columns of the data, i.e., a rectangle, and gives a probability p for the occurrence of 1s in the cells of X × Y. A hierarchical tile has additionally a set of exception tiles that specify the probabilities for subrectangles of the original rectangle. If the rows and columns are ordered and X and Y consist of consecutive elements in those orderings, then the tile is geometric; otherwise it is combinatorial. We give a simple randomized algorithm for finding good geometric tiles. Our main result shows that using spectral ordering techniques one can find good orderings that turn combinatorial tiles into geometric tiles. We give empirical results on the performance of the methods.

FP-Bonsai: The Art of Growing and Pruning Small FP-Trees

Abstract: In the context of mining frequent itemsets, numerous strategies have been proposed to push several types of constraints within the most well known algorithms. In this paper, we integrate the recently proposed ExAnte data reduction technique within the FP-growth algorithm. Together, they result in a very efficient frequent itemset mining algorithm that effectively exploits monotone constraints.

Ontoviews: a tool for creating semantic web portals

Abstract: This paper presents a semantic web portal tool OntoViews for publishing RDF content on the web OntoViews provides the portal designer with a content-based search engine server, Ontogator, and a link recommendation system server, Ontodella The user interface is created by combining these servers with the Apache Cocoon framework From the end-user's viewpoint, the key idea of OntoViews is to combine the multi-facet search paradigm, developed within the information retrieval research community, with semantic web RDFS ontologies, and extend the search service with a semantic browsing facility based on ontological reasoning Onto Views is presented from the viewpoints of the end-user, architecture, and implementation The implementation described is modular, easily modified and extended, and provides a good practical basis for creating semantic portals on the web As a proof of concept, application of Onto Views to a deployed semantic web portal is discussed

Six modes of proactive resource management: a user-centric typology for proactive behaviors

Abstract: Proactivity has recently arisen as one of the focus areas within HCI. Proactive systems adhere to two premises: 1) working on behalf of, or pro, the user, and 2) acting on their own initiative. To extend researchers' views on how proactive systems can support the user, we clarify the concept of proactivity and suggest a typology that distinguishes between 6 modes of proactive resource management: preparation, optimization, advising, manipulation, inhibition, and finalization of user's resources. A scenario of mobile imaging is presented to illustrate how the typology can support the innovation of new use purposes. We argue that conceptual developments like the one proposed here are crucial for the advancement of the emerging field.

InfoRadar: group and public messaging in the mobile context

Abstract: Previous research has sought to utilize everyday messaging metaphors, such as the notice board, in location-based messaging systems. Unfortunately, many of the restrictions associated with the metaphors have been unnecessarily reintroduced to interaction, and results from the previous field trials have been disheartening. InfoRadar builds on experiences with these systems by presenting improvements in user interface functionality and services. By providing a novel radar interface for accessing messages, desktop-like temporal storage for messages, location-independent message threading, filtering functionality, contextual audience addressing, multimedia messaging, social activity indicator, and voting, InfoRadar attempts to combine both public and in-group messaging into one system. A preliminary field trial indicates that location-based aspects may have a role in facilitating mobile communication, particularly when it comes to engaging in social interaction with unknown people.

InfoRadar: group and public messaging in the mobile context

Abstract: Previous research has sought to utilize everyday messaging metaphors, such as the notice board, in location-based messaging systems. Unfortunately, many of the restrictions associated with the metaphors have been unnecessarily reintroduced to interaction, and results from the previous field trials have been disheartening. InfoRadar builds on experiences with these systems by presenting improvements in user interface functionality and services. By providing a novel radar interface for accessing messages, desktop-like temporal storage for messages, location-independent message threading, filtering functionality, contextual audience addressing, multimedia messaging, social activity indicator, and voting, InfoRadar attempts to combine both public and in-group messaging into one system. A preliminary field trial indicates that location-based aspects may have a role in facilitating mobile communication, particularly when it comes to engaging in social interaction with unknown people.

Finding meaningful uses for context-aware technologies: the humanistic research strategy

Abstract: Human-computer interaction (HCI) is undergoing a paradigm change towards interaction that is contextually adapted to rich use situations taking place "beyond the desktop". Currently, however, there are only few successful applications of context-adapted HCI, arguably because use scenarios have not been based on holistic understanding of the society, users, and use situations. A humanistic research strategy, utilized at the Helsinki Institute for Information Technology, aims to structure the innovation and evaluation of scenarios for future technologies. Population trends and motivational needs are analyzed to recognize psycho-socially relevant design opportunities. Ethnography, ethnomethodology, bodystorming, and computer simulations of use situations are conducted to understand use situations. The goal of design is to empower users by supporting their autonomy and control. Three design cases illustrate the approach. The paper showcases an emerging framework for informed innovation of use potentials.

Modelling routing in wireless ad hoc networks with dynamic Bayesian games

Abstract: Mobile agents acting in wireless ad hoc networks are energy constrained, which leads to potential selfishness as nodes are not necessarily willing to forward packets for other nodes. Situations like this are traditionally analyzed using game theory and recently also the ad hoc networking community has witnessed game-theoretic approaches to especially routing. However, from a theoretical point-of-view the contemporary game-theoretic approaches have mainly ignored two important aspects: non-simultaneous decision making and incorporating history information into the decision making process. In this article we propose a new model that fills these gaps and allows to analyze routing theoretically.

Psychologically targeted persuasive advertising and product information in e-commerce

Abstract: In this paper, we describe a framework for a personalization system to systematically induce desired emotion and attention related states and promote information processing in viewers of online advertising and e-commerce product information. Psychological Customization entails personalization of the way of presenting information (user interface, visual layouts, modalities, structures) per user to create desired transient psychological effects and states, such as emotion, attention, involvement, presence, persuasion and learning. Conceptual foundations and empiric evidence for the approach are presented.

A cognitive meta-analysis of design approaches to interruptions in intelligent environments

Abstract: Minimizing interruptions to users is a crucial and acknowledged precondition for the adoption of new intelligent technologies such as ubiquitous and proactive computing. This paper takes a step toward achieving a consensus among the numerous existing approaches addressing the challenge posed by interruptions. We start by explicating why interruptions are considered important. We then reveal similarities and differences among the approaches from a cognitive viewpoint. It appears that the approaches draw from different assumptions about human cognition. Some of the approaches contain inconsistencies. The cognitive analysis also inspires directions for future work.

A Scalable Topic-Based Open Source Search Engine

Abstract: Site-based or topic-specific search engines work with mixed success because of the general difficulty of the information retrieval task, and the lack of good link information to allow authorities to be identified. We are advocating an open source approach to the problem due to its scope and need for software components. We have adopted a topic-based search engine because it represents the next generation of capability. This paper outlines our scalable system for site-based or topic-specific search, and demonstrates the developing system on a small 250,000 document collection of EU and UN web pages.

Linguistic feature extraction using independent component analysis

Abstract: Our aim is to find syntactic and semantic relationships of words based on the analysis of corpora. We propose the application of independent component analysis, which seems to have clear advantages over two classic methods: latent semantic analysis and self-organizing maps. Latent semantic analysis is a simple method for automatic generation of concepts that are useful, e.g., in encoding documents for information retrieval purposes. However, these concepts cannot easily be interpreted by humans. Self-organizing maps can be used to generate an explicit diagram which characterizes the relationships between words. The resulting map reflects syntactic categories in the overall organization and semantic categories in the local level. The self-organizing map does not, however, provide any explicit distinct categories for the words. Independent component analysis applied on word context data gives distinct features which reflect syntactic and semantic categories. Thus, independent component analysis gives features or categories that are both explicit and can easily be interpreted by humans. This result can be obtained without any human supervision or tagged corpora that would have some predetermined morphological, syntactic or semantic information.

Exploring Independent Trends in a Topic-Based Search Engine

Abstract: Topic-based search engines are an alternative to simple keyword search engines that are common in today's intranets. The temporal behaviour of the topics in a topic model based search engine can be used for trend analysis, which is an important research goal on its own. We apply topic modelling to an online financial newspaper data and show that some of the trends in the topics are consistent with common understanding.

System architecture for psychological customization of communication technology

Abstract: Personalization is a process that changes the functionality, interface, information content, or appearance of a system to increase its personal relevance to an individual Personalization systems accommodate individual's needs and interests explicitly through changes and selections initiated by the user, and implicitly through automatic adaptation techniques Currently most of the emphasis in personalization systems is geared towards the utilitarian aspects of personalized information delivery However, what is lacking is the customization of information based on its likely emotional and cognitive effects on different users of communication technology Information presented to individual users or a group of users may be customized on the basis of the immediate emotional and cognitive types of psychological effects it is likely to enable or create in certain individuals or groups Both content and its way of presentation (modality, visual layouts, ways of interaction, structure) may be varied Despite obvious complexities empirical evidence suggests that the way of presenting information to certain psychological profiles has predictable psychological effects For instance, one may facilitate positive emotion for users with certain personality type or more efficient learning for certain cognitive styles This is the basic concept of mind-based technologies Psychological customization may be considered an operationalization and technique of implementing the concept of mind-based technologies in system design Psychological customization may be used for controlling social interaction-centric and individual-centric influence of the content and way of presentation of information on consequent and transient emotional and cognitive effects This paper explores the design space and presents a basic system architecture to implement psychological customization

Towards psychological customization of information for individuals and social groups

Abstract: 1. INTRODUCTION When perceiving information via media and communications technologies, the mind is psychologically transported into a quasi-natural experience of the events described. This is called presence. In presence, information becomes the focused object of perception, while the immediate, external context, including the technological device, fades into the background (Biocca and Levy, 1995; Lombard and Ditton, 1997; Lombard et al, 2000). Various empirical studies show that information experienced in presence has real psychological effects on perceivers, such as emotion based on the events described or cognition of making sense of the events and learning about them (Reeves and Nass, 1996). When using collaborative technology for computer-mediated social interaction, the users experience a state called social presence during which users may, for instance, experience intimacy of interaction or feeling of togetherness in virtual space (Lombard and Ditton, 1997; Lombard et al, 2000). During social presence users also experience various other types of emotional and cognitive effects, such as interpersonal emotion, emotion based on being successful at the task at hand and learning from shared activities or shared information. However, in the context of HCI the psychological effects occurring in computer mediated social interaction have not been thoroughly researched. Moreover, there is a need to integrate and implement the mind-based individual-centric and social interaction-centric approaches to emotional and cognitive effects at the level of system design. Communication systems may be considered as consisting of three layers (Benkler, 2000). At the bottom is a

Towards socially aware pervasive computing: a turntaking approach

Abstract: Social context is an important yet an under-researched area in context-sensitive computing. This paper adopts a framework from social sciences that views social context as a sequence of turns taken between participants. The approach is illustrated and evaluated through three empirical cases. The results show that social context is not a static and passive surrounding of a device, but dynamic and constructed by people. Challenges and restrictions for modelling social context through turntaking are identified.

DiMaS: distributing multimedia on peer-to-peer file sharing networks

Abstract: This demonstration presents the Digital Content Distribution Management System (DiMaS). DiMaS proves as a concept that it is possible to make a system for multimedia producing communities to publish their work on highly popular P2P networks, and importantly, the system enables producers to insert content metadata, to manage intellectual property and usage rights, and to charge for the consumption. All this can be done without introducing another new content or metadata file format and a dedicated client application to read the format.

The role of the learning platform in student-centred e-learning

Abstract: It is often a case that technologically-oriented research on e-learning stresses the tools and individual features used in e-learning platforms rather than the pedagogical model and the underlying course structures. This study compares the outcomes from a similar course in a similar setting using very different learning platforms designed by the same research group. The tool used in the first course, EDUCO, offers awareness of other learners by real-time social navigation features. The tool used in the second course, EDUCOSM, relies on easy-to-make joint asynchronous annotations on documents. The pedagogical model for the courses was the same: student-centered learning in self-organizing and self-evolving groups using peer support to tackle open-ended large problems. The results suggest that the learning outcomes can vary, especially in a case where the environment is open and transparent in a sense that it enables learners to easily rely on and help each other in peer-to-peer fashion.