Recently, online vendors and providers manage review systems as a mechanism to advertise their services and goods over the Web. In making their choice, clients can rely on feedback expressing the degree of satisfaction of past users with respect to such services and goods. This set of feedback, or reviews, may be filtered by categories of users, they may be affected by multiple factors, and they are elaborated in order to obtain an overall score, representing a global indicator aimed at summarising the level of quality of that service. In this paper, we concentrate on multi-factor review,~\ie a review whose value is computed assembling the scores given to a set of parameters that may affect the quality level of a service. Our interest is evaluating the relevance, or dominance, of some parameter with respect to the others. We advocate the use of the Analytic Hierarchy Process, a well-known technique born in the area of multi-criteria decision making, to derive the priorities to assign to the scores of the single parameters. We illustrate the proposal on the example of hotel reviews.

This paper describes an attempt to provide more intelligence to industrial robotics and automation systems. We develop an architecture to integrate disparate knowledge representations used in different places in robotics and automation. This knowledge integration framework, a possibly distributed entity, abstracts the components used in design or production as data sources, and provides a uniform access to them via standard interfaces. Representation is based on the ontology formalizing the process, product and resource triangle, where skills are considered the common element of the three. Production knowledge is being collected now and a preliminary version of KIF undergoes verification.

Functionality makes APIs unique and therefore helps humans and machines decide what service they need. However, if two APIs offer similar functionality, quality attributes such as performance and ease-of-use might become a decisive factor. Several of these quality attributes are inherently subjective, and hence exist within a social context. These social parameters should be taken into account when creating personalized mashups and service compositions. The Web API description format RESTdesc already captures functionality in an elegant way, so in this paper we will demonstrate how it can be extended to include social parameters. We indicate the role these parameters can play in generating functional compositions that fulfill specified quality attributes. Finally, we show how descriptions can be personalized by exploring a user’s social graph. This ultimately leads to a more focused, on-demand use of Web APIs, driven by functionality and social parameters.

Service composition, which achieves the goal of value-added services, has been considered as the core technique of Service-oriented Computing (SOC). To cope with the challenge of ever-increasing number of web services, graph-based web service network has emerged as a potential solution to the state of art SOC. In such a way, composite services are constructed by applying searching algorithms to the built graph, and proved to achieve outstanding performance in complexity. However, web service network suffers two crucial disadvantages: poor connectivity and negative links, and both of them have crucial negative impact on service composition. To cope with the problems, we propose two methods in this paper. Firstly, leveraging social network analysis, we focus on enriching web service network by adding valuable services, which will play positive roles in solving poor connective problem. Secondly, we show a serious status that numerous negative links contained in the underlying networks, and then we propose to identify and remove the negative links based on users’ historical composite services.

The importance of diversity in reasoning and learning to successfully address complex problems is examined. We discuss an approach by which a multiagent framework with decentralized control mechanisms provides diverse perspectives and hypotheses addressing a class of complex problems. We introduce the SNARE multiagent system. SNARE performs tasks to gain situational awareness of situations of interest in a Social Media Space. It applies a decentralized control mechanism for each agent; this mechanism enables an agent to interact with other agents to reason and learn. This approach facilitates dynamic agent organizations that adapt the topologies of interactions between agents based on the problem context.

The Web is a giant repository of resources (Service and content), where Discovery and Recommendation systems are used to deliver the best ranked list of relevant web resources that meet user requirements. Nowadays, these systems are based on the simulation and automation of the user search criteria, considering the relation between consumption trends and the different kinds of users’ relationships with their virtual and physical environment, based on the information from the Social Web and mobile device sensors among others. These systems are executed once an explicit query of the user has been received; however, there are resources that are useful in specific situations, where these resources have high probability to be consumed, but, due to absence of a query they are not recommended to the users. In this regard, the question is: how to make a successful Web Resource Recommendation without the user query? In order to answer the question, this research proposal presents a novel approach to Recommend Web Resources based on Dynamic Prediction of User Consumption on the Social Web, which emulates the user behavior, the resource dynamism and the context opportunities, in real time, catching the best situations to make an asynchronous (unexpected by the user) recommendation of a useful Resources; and boost Web Resources consumption.

We consider the two problems of predicting links in a dynamic graph sequence and predicting functions defined at each node of the graph. In many applications, the solution of one problem is useful for solving the other. Indeed, if these functions reflect node features, then they are related through the graph structure. In this paper, we formulate a hybrid approach that simultaneously learns the structure of the graph and predicts the values of the node-related functions. Our approach is based on the optimization of a joint regularization objective. We empirically test the benefits of the proposed method with both synthetic and real data. The results indicate that joint regularization improves prediction performance over the graph evolution and the node features.

File type identification and file type clustering may be difficult tasks that have an increasingly importance in the field of computer and network security. Classical methods of file type detection including considering file extensions and magic bytes can be easily spoofed. Content-based file type detection is a newer way that is taken into account recently. In this paper, a new content-based method for the purpose of file type detection and file type clustering is proposed that is based on the PCA and neural networks. The proposed method has a good accuracy and is fast enough.

We present a probabilistic model of events in continuous time in which each event triggers a Poisson process of successor events. The ensemble of observed events is thereby modeled as a superposition of Poisson processes. Efficient inference is feasible under this model with an EM algorithm. Moreover, the EM algorithm can be implemented as a distributed algorithm, permitting the model to be applied to very large datasets. We apply these techniques to the modeling of Twitter messages and the revision history of Wikipedia.

Most conventional Reinforcement Learning (RL) algorithms aim to optimize decision-making rules in terms of the expected returns. However, especially for risk management purposes, other risk-sensitive criteria such as the value-at-risk or the expected shortfall are sometimes preferred in real applications. Here, we describe a parametric method for estimating density of the returns, which allows us to handle various criteria in a unified manner. We first extend the Bellman equation for the conditional expected return to cover a conditional probability density of the returns. Then we derive an extension of the TD-learning algorithm for estimating the return densities in an unknown environment. As test instances, several parametric density estimation algorithms are presented for the Gaussian, Laplace, and skewed Laplace distributions. We show that these algorithms lead to risk-sensitive as well as robust RL paradigms through numerical experiments.