Florian Geigl

Ever since the inception of the Web website administrators have tried to steer user browsing behavior for a variety of reasons. For example, to be able to provide the most relevant information, for offering specific products, or to increase revenue from advertisements. One common approach to steer or bias the browsing behavior of users is to influence the link selection process by, for example, highlighting or repositioning links on a website. In this paper, we present a methodology for (i)… Mehr anzeigen

Ever since the inception of the Web website administrators have tried to steer user browsing behavior for a variety of reasons. For example, to be able to provide the most relevant information, for offering specific products, or to increase revenue from advertisements. One common approach to steer or bias the browsing behavior of users is to influence the link selection process by, for example, highlighting or repositioning links on a website. In this paper, we present a methodology for (i) expressing such navigational biases based on the random surfer model, and for (ii) measuring the consequences of the implemented biases. By adopting a model-based approach we are able to perform a wide range of experiments on seven empirical datasets. Our analyses allows us to gain novel insights into the consequences of navigational biases. Further, we unveil that navigational biases may have significant effects on the browsing processes of users and their typical whereabouts on a website. The first contribution of our work is the formalization of an approach to analyze consequences of navigational biases on the browsing dynamics and visit probabilities of specific pages of a website. Second, we apply this approach to analyze several empirical datasets and improve our understanding of the effects of different biases on real-world websites. In particular, we find that on webgraphs—contrary to undirected networks—typical biases always increase the certainty of the random surfer when selecting a link. Further, we observe significant side effects of biases, which indicate that for practical settings website administrators might need to carefully balance the desired outcomes against undesirable side effects. Weniger anzeigen

Many online collaboration networks struggle to gain user activity and become self-sustaining due to the ramp-up problem or dwindling activity within the system. Prominent examples include online encyclopedias such as (Semantic) MediaWikis, Question and Answering portals such as StackOverflow, and many others. Only a small fraction of these systems manage to reach self-sustaining activity, a level of activity that prevents the system from reverting to a nonactive state. In this article, we model… Mehr anzeigen

Many online collaboration networks struggle to gain user activity and become self-sustaining due to the ramp-up problem or dwindling activity within the system. Prominent examples include online encyclopedias such as (Semantic) MediaWikis, Question and Answering portals such as StackOverflow, and many others. Only a small fraction of these systems manage to reach self-sustaining activity, a level of activity that prevents the system from reverting to a nonactive state. In this article, we model and analyze activity dynamics in synthetic and empirical collaboration networks. Our approach is based on two opposing and well-studied principles: (i) without incentives, users tend to lose interest to contribute and thus, systems become inactive, and (ii) people are susceptible to actions taken by their peers (social or peer influence). With the activity dynamics model that we introduce in this article we can represent typical situations of such collaboration networks. For example, activity in a collaborative network, without external impulses or investments, will vanish over time, eventually rendering the system inactive. However, by appropriately manipulating the activity dynamics and/or the underlying collaboration networks, we can jump-start a previously inactive system and advance it toward an active state. To be able to do so, we first describe our model and its underlying mechanisms. We then provide illustrative examples of empirical datasets and characterize the barrier that has to be breached by a system before it can become self-sustaining in terms of critical mass and activity dynamics. Additionally, we expand on this empirical illustration and introduce a new metric p—the Activity Momentum—to assess the activity robustness of collaboration networks. Weniger anzeigen

Websites have an inherent interest in steering user navigation in order to, for example, increase sales of specific products or categories, or to guide users towards specific information. In general, website administrators can use the following two strategies to influence their visitors' navigation behavior. First, they can introduce click biases to reinforce specific links on their website by changing their visual appearance, for example, by locating them on the top of the page. Second, they… Mehr anzeigen

Websites have an inherent interest in steering user navigation in order to, for example, increase sales of specific products or categories, or to guide users towards specific information. In general, website administrators can use the following two strategies to influence their visitors' navigation behavior. First, they can introduce click biases to reinforce specific links on their website by changing their visual appearance, for example, by locating them on the top of the page. Second, they can utilize link insertion to generate new paths for users to navigate over. In this paper, we present a novel approach for measuring the potential effects of these two strategies on user navigation. Our results suggest that, depending on the pages for which we want to increase user visits, optimal link modification strategies vary. Moreover, simple topological measures can be used as proxies for assessing the impact of the intended changes on the navigation of users, even before these changes are implemented. Weniger anzeigen

The Internet Movie Database (IMDb) is the world's largest collection of facts about movies and features large-scale recommendation systems connecting hundreds of thousands of items. In the past, the principal evaluation criterion for such recommender systems has been the rating accuracy prediction for recommendations within the immediate one-hop-neighborhood. Apart from a few isolated studies, the evaluation methodology for recommender systems has so far lacked approaches that quantify and… Mehr anzeigen

The Internet Movie Database (IMDb) is the world's largest collection of facts about movies and features large-scale recommendation systems connecting hundreds of thousands of items. In the past, the principal evaluation criterion for such recommender systems has been the rating accuracy prediction for recommendations within the immediate one-hop-neighborhood. Apart from a few isolated studies, the evaluation methodology for recommender systems has so far lacked approaches that quantify and measure the exposure to novel content while navigating a recommender system. As such, little is known about the support for navigation and browsing as methods to explore, browse and discover novel items within these systems. In this article, we study the navigability of IMDb's recommender systems over multiple hops. To this end, we analyze the recommendation networks of IMDb with a two-level approach: First, we study reachability in terms of components, path lengths and a bow-tie analysis. Second, we simulate practical browsing scenarios based on greedy decentralized search. Our results show that the IMDb recommendation networks are not very well-suited for navigation scenarios. To mitigate this, we apply a method for diversifying recommendations by specifically selecting recommendations which improve connectivity but do not compromise relevance. We demonstrate that this leads to improved reachability and navigability in both recommender systems. Our work underlines the importance of navigability and reachability as evaluation dimension of a large movie recommender system and shows up ways to increase navigational diversity. Weniger anzeigen

The random surfer model is a frequently used model for simulating user navigation behavior on the Web. Various algorithms, such as PageRank, are based on the assumption that the model represents a good approximation of users browsing a website. However, the way users browse the Web has been drastically altered over the last decade due to the rise of search engines. Hence, new adaptations for the established random surfer model might be required, which better capture and simulate this change in… Mehr anzeigen

The random surfer model is a frequently used model for simulating user navigation behavior on the Web. Various algorithms, such as PageRank, are based on the assumption that the model represents a good approximation of users browsing a website. However, the way users browse the Web has been drastically altered over the last decade due to the rise of search engines. Hence, new adaptations for the established random surfer model might be required, which better capture and simulate this change in navigation behavior. In this article we compare the classical uniform random surfer to empirical navigation and page access data in a Web Encyclopedia. Our high level contributions are (i) a comparison of stationary distributions of different types of the random surfer to quantify the similarities and differences between those models as well as (ii) new insights into the impact of search engines on traditional user navigation. Our results suggest that the behavior of the random surfer is almost similar to those of users---as long as users do not use search engines. We also find that classical website navigation structures, such as navigation hierarchies or breadcrumbs, only exercise limited influence on user navigation anymore. Rather, a new kind of navigational tools (e.g., recommendation systems) might be needed to better reflect the changes in browsing behavior of existing users. Weniger anzeigen

In this paper, we analyze the influence of social status on opinion dynamics and consensus building in collaboration networks. To that end, we simulate the diffusion of opinions in empirical collaboration networks by taking into account both the network structure and the individual differences of people reflected through their social status. For our simulations, we adapt a well-known Naming Game model and extend it with the Probabilistic Meeting Rule to account for the social status of… Mehr anzeigen

In this paper, we analyze the influence of social status on opinion dynamics and consensus building in collaboration networks. To that end, we simulate the diffusion of opinions in empirical collaboration networks by taking into account both the network structure and the individual differences of people reflected through their social status. For our simulations, we adapt a well-known Naming Game model and extend it with the Probabilistic Meeting Rule to account for the social status of individuals participating in a meeting. This mechanism is sufficiently flexible and allows us to model various situations in collaboration networks, such as the emergence or disappearance of social classes. In this work, we concentrate on studying three well-known forms of class society: egalitarian, ranked and stratified. In particular, we are interested in the way these society forms facilitate opinion diffusion. Our experimental findings reveal that (i) opinion dynamics in collaboration networks is indeed affected by the individuals' social status and (ii) this effect is intricate and non-obvious. In particular, although the social status favors consensus building, relying on it too strongly can slow down the opinion diffusion, indicating that there is a specific setting for each collaboration network in which social status optimally benefits the consensus building process. Weniger anzeigen

Due to sheer size of today’s information and social
networks people and algorithms are limited in their knowledge
about those networks. Since this knowledge is important in many
processes taking place on such network, e.g. search and navigation,
an interesting question is how this fractional knowledge
should be constituted and structured. For example, when agents
navigate an information network the question is what are the
most important nodes for an efficient navigation… Mehr anzeigen

Due to sheer size of today’s information and social
networks people and algorithms are limited in their knowledge
about those networks. Since this knowledge is important in many
processes taking place on such network, e.g. search and navigation,
an interesting question is how this fractional knowledge
should be constituted and structured. For example, when agents
navigate an information network the question is what are the
most important nodes for an efficient navigation. In this paper we
apply machine learning techniques to learn an optimal division
of network nodes into two classes: nodes that are important for
navigation and nodes that are not important for navigation. We
learn this optimal classification by maximizing the correlation
between global and fractional knowledge about a network.
For learning we resort to MCMC methods such as Simulated
Annealing and a simple approach for random assignment of
nodes to classes. We perform a series of experiments by applying
our optimization algorithm to synthetic networks with different
community structures to shed more light into the relation between
network structure, the node structural properties such as various
centrality measures, and node classes produced by the algorithm. Weniger anzeigen

When searching for specific nodes in a network an agent hops from one node to another by traversing network links. If the network is large, the agent typically possesses partial background knowledge or certain intuitions about the network. This background knowledge steers the agent’s decisions when selecting the link to traverse next. In previous research two types of background knowledge have been applied to design and evaluate search algorithms: homophily (node similarity) and node popularity… Mehr anzeigen

When searching for specific nodes in a network an agent hops from one node to another by traversing network links. If the network is large, the agent typically possesses partial background knowledge or certain intuitions about the network. This background knowledge steers the agent’s decisions when selecting the link to traverse next. In previous research two types of background knowledge have been applied to design and evaluate search algorithms: homophily (node similarity) and node popularity (typically represented by the degree of the node). In this paper we present a method for evaluating the relative importance of those two features for an efficient network search. Our method is based on a probabilistic model that represents those two features as a mixture distribution, i.e. as a convex combination of link selection probabilities based on the candidate node popularity and similarity to a given target node in the network. We also demonstrate this method by analyzing four networks, including social as well as information networks. Finally, we analyze strategies for dynamically adapting the mixture distribution during navigation. The goal of our analysis is to shed more light into appropriate configurations of the background knowledge for efficient search in various networks. The preliminary results provide promising insights into the influence of structural features on network search efficiency. Weniger anzeigen