No abstract

We consider the problem of 1 identifying product features and opinion words in a unified process from Chinese customer reviews when only a much small seed set of opinion words is available. In particular, we consider a problem setting motivated by the task of identifying product features with opinion words and learning opinion words through features alternately and iteratively. In customer reviews, opinion words usually have a close relationship with product features, and the association between them is measured by a revised formula of mutual information in this paper. A bootstrapping iterative learning strategy is proposed to alternately both of them. A linguistic rule is adopted to identify lowfrequent features and opinion words. Furthermore, a mapping function from opinion words to features is proposed to identify implicit features in sentence. Empirical results on three kinds of product reviews indicate the effectiveness of our method.

Emotions are part and parcel of human life and among other things, highly influence decision making. Computers have been used for decision making for quite some time now but have traditionally relied on factual information.Recently, interest has been growing among researchers to find ways of detecting subjective information used in blogs and other online social media. This paper presents emotion theories that provide a basis for emotion models. It shows how these models have been used by discussing computational approaches to emotion detection. We propose a hybrid based architecture for emotion detection. The SVM algorithm is used for validating the proposed architecture and achieves a prediction accuracy of 96.43% on web blog data.

SUMMARYThe recent development of Web-of-Things (WoT) and Cyber-Physical Systems (CPS) raises a new requirement of connecting abstract computational artifacts with the physical world. This requires both new theories and engineering practices that model cyber and physical resources in a unified framework, a challenge that few current approaches are able to tackle. The solution must break the boundary between the cyber world and the physical world by providing a unified infrastructure that permits integrated models addressing issues from both worlds simultaneously. This paper proposes a framework to integrate WoT and CPS. A case study is presented to demonstrate the advantage of the framework.

No abstract

No abstract

This paper critically evaluates existing work, presents an opinion mining framework and exposes new areas of research in opinion mining. Individuals, businesses and government can now easily know the general opinion prevailing on a product, company or public policy. At the core of this field is semantic orientation of subjective terms in documents or reviews which seeks to establish their contextual connotation through opinion mining. Overall item sentiment can be expressed based on its sentiment words in general or by specifically identifying its features and the opinions being expressed about them. This leads us to the motivation of the framework for opinion mining and categorizing current literature in such a manner as to make clear, research opportunities. The freedom offered by the web as a platform for presenting opinions on any subject brings with it many new opportunities.

Cloud services are becoming popular in terms of distributed technology because they allow cloud users to rent well-specified resources of computing, network, and storage infrastructure. Users pay for their use of services without needing to spend massive amounts for integration, maintenance, or management of the IT infrastructure. This creates the need for a reliable measurement methodology of the scalability for this type of new paradigm of services. In this paper, we develop performance metrics to measure and compare the scalability of the resources of virtualization on the cloud data centres. First, we discuss the need for a reliable method to compare the performance of cloud services among a number of various services being offered. Second, we develop a different type of metrics and propose a suitable methodology to measure the scalability using these types of metrics. We focus on the visualization resources such as CPU, storage disk, and network infrastructure. Finally, we compare well-known cloud providers using the proposed approach and conclude the recommendations. This type of research will help cloud consumers, before signing any official contract to use the desired services, to ascertain the ability and capacity of the cloud providers to deliver a particular service.