Unter Web Monitoring versteht man die zielgerichtete Beobachtung, Extraktion, Analyse und Aufbereitung von Nennungen zu Unternehmen, Marken, Produkten, Personen, Nachrichten oder Themen. Web Monitoring dient den Unternehmen, Organisationen und Nutzern der Meinungsforschung sowie dem Brand und Reputation Management. Mit der Hilfe von Key Performance Indicators lassen sich individuelle Webziele, Unternehmensziele oder Maßnahmen über die Zeit verfolgen, um steuernd in die Meinungsbildungsprozesse im Web eingreifen zu können.
Das Schwerpunktheft »Web Monitoring« bietet Ihnen Grundlagen, Forschungs- und Praxisberichte aus dem aufstrebenden Gebiet, das zwischen Wirtschaftsinformatik, Marketing sowie Medien- und Kommunikationswissenschaften angesiedelt werden kann. Es dient Ihnen dazu, das Potenzial webbasierter Analysewerkzeuge für Social Media besser einschätzen und die Chancen und Risiken fundierter abwägen zu können. Konkret werden u.a. folgende Teilthemen behandelt:
– State-of-the-Art Web Monitoring
– Einsatz erweiterter Empfehlungssysteme in Onlineshops
– Process Mining mit Fallstudie zu einer Übersetzungsplattform
– Retourenvermeidung durch Web Monitoring
– Entwicklung zielkonformer Social-Media-Strategie
Web Monitoring gewinnt immer mehr an Bedeutung. Das World Wide Web enthält strategisch relevante Informationen für Unternehmen und Organisationen. Durch gezieltes Beobachten ausgewählter Quellen im Web können Produktportfolios optimiert und sogar neue Geschäftsfelder entdeckt werden. Dieser Beitrag gibt eine Einführung in die Kernprozesse des Web Monitoring und zeigt auf, welche Elemente bei der Planung eines Web-Monitoring-Projekts wichtig sind.
The Role of Trends in Evolving Networks
Preprint on arxiv.org
Modeling complex networks has been the focus of much research for over a decade –. Preferential attachment (PA)  is considered a common explanation to the self organization of evolving networks, suggesting that new nodes prefer to attach to more popular nodes. The PA model results in broad degree distributions, found in many networks, but cannot explain other common properties such as: The growth of nodes arriving late  and Clustering (community structure). Here we show that when the tendency of networks to adhere to trends is incorporated into the PA model, it can produce networks with such properties. Namely, in trending networks, newly arriving nodes may become central at random, forming new clusters. In particular, we show that when the network is young it is more susceptible to trends, but even older networks may have trendy new nodes that become central in their structure. Alternatively, networks can be seen as composed of two parts: static, governed by a power law degree distribution, and a dynamic part governed by trends, as we show on Wiki pages. Our results also show that the arrival of trending new nodes not only creates new clusters, but also has an effect on the rel- ative importance and centrality of all other nodes in the network. This can explain a variety of real world networks in economics, social and online networks, and cultural networks. Products popularity, formed by the network of people’s opinions, exhibit these properties. Some lines of products are increasingly susceptible to trends and hence to shifts in popularity, while others are less trendy and hence more stable. We believe that our findings have a big impact on our understanding of real networks.
Preferential Attachment in Online Networks: Measurement and Explanations
Accepted @Web Science Conference Paris, 2nd – 5th May, 2013
In this paper we performed an empirical study of the preferential attachment phenomenon in temporal networks and show that on the Web, networks follow a nonlinear preferential attachment model in which the exponent depends on the type of network considered. The classical preferential attachment model for networks (Barabasi and Albert 1999) assumes a linear relationship between the number of neighbours of a node in network and the probability of attachment.
Although this assumption is widely made in Web Science and related fields, the underlying linearity is rarely measured. We performed an empirical longitudinal (time-based) study on forty-seven diverse Web network datasets from seven network categories. We show that contrary to the usual assumption, preferential attachment is nonlinear in the networks under consideration. We observe a dependency between the non linearity and the type of network under consideration – sublinear preferential attachment in certain types of networks, and superlinear attachment in others.
We propose explanations for the behaviour of that network measure, based on the mechanisms underlying the growth of the network in question.
Recommendation systems in the scope of opinion formation: a model
Presented at RecSys Conference 2012 Dublin
Aggregated data in real world recommender applications of- ten feature fat-tailed distributions of the number of times individual items have been rated or favored. We propose a model to simulate such data. The model is mainly based on social interactions and opinion formation taking place on a complex network with a given topology. A threshold mechanism is used to govern the decision making process that determines whether a user is or is not interested in an item. We demonstrate the validity of the model by fitting attendance distributions from different real data sets. The model is mathematically analyzed by investigating its master equation. Our approach provides an attempt to understand recommender system’s data as a social process. The model can serve as a starting point to generate artificial data sets useful for testing and evaluating recommender systems.
Full Paper, Presentation
Recommendation System for Continuing Education Courses
Presented at the Workshop on Data Analysis and Interpretation for Learning Environments (DAILE13)
Continuing Education represents the totality of learning pro- cesses thanks to which people enrich their knowledge and personal skills or orient their personal qualifications on the basis of individual needs and those of society. The SUPSI (Scuola Universitaria della Svizzera Italiana) offers continu- ing education courses for the upgrading, improvement, and specialization of professionals throughout their careers (life long learning) in the fields of construction, energy and envi- ronment, design, engineering, teacher training, health, man- agement, tax law, social sciences, music and theater. The SUPSI Continuing Education website (http://www.supsi. ch/fc/corsi.html) gives to its users the opportunity to reg- ister their profile, indicate their areas of interest, and view the courses attended in the past. The number of courses of- fered is huge and this leads to a difficult choice for the users. For this reason it would be useful that the site could recom- mend relevant courses for every user in a personalized way. In this paper we propose a hybrid recommender system that combines a network-based and a content-based method and we applied it to the SUPSI Continuing Education Database.
B-Rank: A top N Recommendation Algorithm
Presented at Complexity, Informatics and Cybernetics Conference Orlando USA, 2010
In this paper B-Rank, an efficient ranking algorithm for recommender systems, is proposed. B-Rank is based on a random walk model on hypergraphs. Depending on the setup, B-Rank outperforms other state of the art algo- rithms in terms of precision, recall ∼ (19% − 50%) and inter list diversity ∼ (20% − 60%). B-Rank captures well the difference between popular and niche objects. The proposed algorithm produces very promising results for sparse and dense voting matrices. Furthermore, a recom- mendation list update algorithm is introduced,to cope with new votes. This technique significantly reduces computa- tional complexity. The algorithm implementation is sim- ple, since B-Rank needs no parameter tuning.
Heat Conduction Process on Community Networks as a Recommendation Model
Published in Phys.Rev.Lett.99.154301
Using heat conduction mechanism on a social network we develop a systematic method to predict missing values as recommendations. This method can treat very large matrices that are typical of internet communities. In particular, with an innovative, exact formulation that accommodates arbitrary boundary condition, our method is easy to use in real applications. The performance is assessed by comparing with traditional recommendation methods using real data.
Dodes (diagnostic nodes) for Guideline Manipulation
Published in Journal of Radiation Oncology Informatics
Treatment recommendations (guidelines) are commonly represented in text form. Based on parameters (questions) recommendations are defined (answers). Objectives: To improve handling, alternative forms of representation are required. Methods: The concept of Dodes (diagnostic nodes) has been developed. Dodes contain answers and questions. Dodes are based on linked nodes and additionally contain descriptive information and recommendations. Dodes are organized hierarchically into Dode trees. Dode categories must be defined to prevent redundancy. Results: A centralized and neutral Dode database can provide standardization, which is a requirement for the comparison of recommendations. Centralized administration of Dode categories can provide information about diagnostic criteria (Dode categories) underutilized in existing recommendations (Dode trees). Conclusions: Representing clinical recommendations in Dode trees improves their manageability, handling and updateability.
Semantic methods to capture Awareness in Business Organizations
Presented at I-KNOW, Graz, Austria
In multifarious offices, where social interaction is necessary in order to share and locate essential information, awareness becomes a concurrent process that amplifies the exigency of easy routes for personnel to be able to access this information, deferred or decentralized, in a formalized and context-sensitive way. Although the subject of awareness has immensely grown in importance, there is extensive disagreement about how this transparency can be conceptually and technically implemented. This paper introduces an awareness model in order to visualize and navigate such information in multi-tiers using semantic networks, and Web3D. To support this concept we introduce two different algorithms. The first algorithm is able to guide individuals to relevant information and topics. The second one is able to infer hidden groups (clusters) in a large company network, representing various communication channels between individuals. Both algorithms produce very promising results.
When are recommender system useful
Recommender systems are crucial tools to overcome the information overload brought about by the Internet. Rigorous tests are needed to establish to what extent sophisticated methods can improve the quality of the predictions. Here we analyse a refined correlation-based collaborative filtering algorithm and compare it with a novel spectral method for recommending. We test them on two databases that bear different statistical properties (MovieLens and Jester) without filtering out the less active users and ordering the opinions in time, whenever possible. We find that, when the distribution of user-user correlations is narrow, simple averages work nearly as well as advanced methods. Recommender systems can, on the other hand, exploit a great deal of additional information in systems where external influence is negligible and peoples’ tastes emerge entirely. These findings are validated by simulations with artificially generated data.
Exploring an opinion network for taste prediction: an empirical study
Published in Physica A: Statistical and theoretical Physics Vol. 373
We develop a simple statistical method to find affinity relations in a large opinion network which is represented by a very sparse matrix. These relations allow us to predict missing matrix elements. We test our method on the Eachmovie data of thousands of movies and viewers. We found that significant prediction precision can be achieved and it is rather stable. There is an intrinsic limit to further improve the prediction precision by collecting more data, implying perfect prediction can never obtain via statistical means.