Andreas Geyer-Schulz

Analyzing event stream dynamics in two-mode networks: An exploratory analysis of private communication in a question and answer community

Abstract Information about social networks can often be collected as event stream data. However, most methods in social network analysis are defined for static network snapshots or for panel data. We propose an actor oriented Markov process framework to analyze the structural dynamics in event streams. Estimated parameters are similar to what is known from exponential random graph models or stochastic actor oriented models as implemented in SIENA. We apply the methodology on a question and answer web community and show how the relevance of different kinds of one- and two-mode network structures can be tested using a new software.

Comparing two recommender algorithms with the help of recommendations by peers

Since more and more Web sites, especially sites of retailers, offer automatic recommendation services using Web usage mining, evaluation of recommender algorithms has become increasingly important. In this paper we present a framework for the evaluation of different aspects of recommender systems based on the process of discovering knowledge in databases introduced by Fayyad et al. and we summarize research already done in this area. One aspect identified in the presented evaluation framework is widely neglected when dealing with recommender algorithms. This aspect is to evaluate how useful patterns extracted by recommender algorithms are to support the social process of recommending products to others, a process normally driven by recommendations by peers or experts. To fill this gap for recommender algorithms based on frequent itemsets extracted from usage data we evaluate the usefulness of two algorithms. The first recommender algorithm uses association rules, and the other algorithm is based on the repeat-buying theory known from marketing research. of usage data from an educational Internet information broker and compare useful recommendations identified by users from the target group of the broker (peers) with the recommendations produced by the algorithms. The results of the evaluation presented in this paper suggest that frequent itemsets from usage histories match the concept of useful recommendations expressed by peers with satisfactory accuracy (higher than 70%) and precision (between 60% and 90%). Also the evaluation suggests that both algorithms studied in the paper perform similar on real-world data if they are tuned properly.

Holland classifier systems

A Holland classifier system is an adaptive, general purpose machine learning system which is designed to operate in noisy environments with infrequent and often incomplete feedback. Examples of such environments are financial markets, stock management systems, or chemical processes. In financial markets, a Holland classifier system would develop trading strategies, in a stock management system order heuristics, and in a chemical plant it would perform process control. In this paper we describe a Holland classifier system and present the implementation of its components, namely the production system, the bucket brigade algorithm, the genetic algorithm, and the cover detector, cover effector and triggered chaining operator. Finally, we illustrate the working of a Holland classifier system by learning to find a path with a high payoff in a simple finite state world.

A Customer Purchase Incidence Model Applied to Recommender Services

In this contribution we transfer a customer purchase incidence model for consumer products which is based on Ehrenbergs repeat-buying theory to Web-based information products. Ehrenbergs repeat-buying theory successfully describes regularities on a large number of consumer product markets. We show that these regularities exist in electronic markets for information goods, too, and that purchase incidence models provide a well founded theoretical base for recommender and alert services.The article consists of two parts. In the first part Ehrenbergs repeat-buying theory and its assumptions are reviewed and adapted for web-based information markets. Second, we present the empirical validation of the model based on data collected from the information market of the Virtual University of the Vienna University of Economics and Business Administration from September 1999 to May 2001.

Eigenspectral analysis of hermitian adjacency matrices for the analysis of group substructures

ABSTRACT In this paper we propose the use of the eigensystem of complex adjacency matrices to analyze the structure of asymmetric directed weighted communication. The use of complex Hermitian adjacency matrices allows to store more data relevant to asymmetric communication, and extends the interpretation of the resulting eigensystem beyond the principal eigenpair. This is based on the fact, that the adjacency matrix is transformed into a linear self-adjoint operator in Hilbert space. Subgroups of members, or nodes of a communication network can be characterised by the eigensubspaces of the complex Hermitian adjacency matrix. Their relative ‘traffic-level’ is represented by the eigenvalue of the subspace, and their members are represented by the eigenvector components. Since eigenvectors belonging to distinct eigenvalues are orthogonal the subgroups can be viewed as independent with respect to the communication behavior of the relevant members of each subgroup. As an example for this kind of analysis the EIES data set is used. The substructures and communication patterns within this data set are described.

Recommendations for Virtual Universities from Observed User Behavior

Recently recommender systems started to gain ground in commercial Web-applications. For example, the online-bookseller amazon.com recommends his customers books similar to the ones they bought using the analysis of observed purchase behavior of consumers.

Fuzzy Genetic Algorithms

In this chapter we present a tutorial on fuzzy genetic algorithms applied to control problems. The unifying theme of this chapter is the use of fuzzy genetic algorithms to systematically breed better and better control strategies with simulation models of real-world systems and thus to overcome the limitations of classic analytical and numerical optimization methods. As introduction we present the MIT beer distribution game as an example of a complex dynamic decision-problem. In the following section we introduce simple genetic algorithms at a leisurely pace and show why we use a genetic algorithm for control problems. Next, we proceed to fuzzy genetic algorithms. We restrict our exploration of the design space of genetic algorithms to simple genetic algorithms over fuzzy rule-languages. In section 11.3 we show how such rule-languages can be coded with fixed or variable length strings over arbitrary alphabets. Finally, in section 11.4 we extend the representation of the fuzzy rule-language to genetic programming.

Social Emergency Alert Service - A Location-Based Privacy-Aware Personal Safety Service

The advanced capabilities for location-based services of smart phones are mostly used for travel applications, navigation or business fleet management. We motivate a social emergency alert service that makes use of the wide availability of smart phones and activates nearby social contacts in cases of emergency. Research has shown, that especially in busy urban districts help from fellow citizens is hard to receive because of the so-called bystander-effect: Nearby people often do not recognize or take responsibility for ongoing emergency situations. A simple and fast mechanism to call for help is necessary. Additional to local authorities as the police or rescue services, assistance from family or acquaintances is a valuable and fast(er) supplement. We describe the architecture of an emergency alert service providing the functionality required for the activation of social contacts and present a prototype. The distribution of tasks between mobile devices and server infrastructure and the underlying communication protocol are designed energy-efficient and privacy preserving. The central tracking of geo-positions is avoided.

Collective Intelligence Generation from User Contributed Content

In this paper we provide a foundation for a new generation of services and tools. We define new ways of capturing, sharing and reusing information and intelligence provided by single users and communities, as well as organizations by enabling the extraction, generation, interpretation and management of Collec- tive Intelligence from user generated digital multimedia content. Different layers of intelligence are generated, which together constitute the notion of Collective Intel- ligence. The automatic generation of Collective Intelligence constitutes a departure from traditional methods for information sharing, since information from both the multimedia content and social aspects will be merged, while at the same time the social dynamics will be taken into account. In the context of this work, we present two case studies: an Emergency Response and a Consumers Social Group case study.

myVU: A Next Generation Recommender System Based on Observed Consumer Behavior and Interactive Evolutionary Algorithms

myVU is a next generation recommender system based on observed consumer behavior and interactive evolutionary algorithms implementing customer relationship management and one-to-one marketing in the educational and scientific broker system of a virtual university. myVU provides a personalized, adaptive WWW-based user interface for all members of a virtual university and it delivers routine recommendations for frequently used scientific and educational Web-sites.