Current methods for detecting deception automatically tend to focus on specific words or abstract linguistic features that may not be rooted in the psychology of deception. While these methods can perform well when training and testing data have similar content, they struggle when the content changes. In this study, we explore new features that capture stylistic patterns and sentiments, which are psychologically relevant aspects of truthful and deceptive language that may be useful across different content domains. To assess these features’ potential, we test them on various datasets containing deceptive language, such as hotel, restaurant, and doctor reviews. We also evaluate these features within a deception detection classifier. Our findings show that sentiment-based features are most effective for cross-domain deception detection when the content of training and testing data significantly differs, and they especially improve classification accuracy on deceptive documents. The results have implications for developing general-purpose deception detection approaches.

Deceptive Opinion Spam commonly takes the form of fake reviews (negative or positive) posted by a malicious web user to hurt or inflate a company's image. As these reviews have been deliberately written to deceive the reader, human reviewers are faring little better than a chance in detecting these deceptive statements. Thus, there is a dire need to address this issue as extracting text patterns from the fraudulent texts with meaningful substructures still remains a challenge. In our research, to obtain a deeper understanding of how lies are expressed in texts, we consider the task as a topic modeling problem, in which we constructed a model to learn the patterns that constitute a fake review, and then explore the outputs of this model to identify those patterns. Topic models may be useful in this task due to their ability to group multiple documents into smaller sets of key topics. As the linguistic cues of the lies are still unknown, a key advantage of this approach is that the algorithm encourages the mixtures composed of only few topics, which makes the representation more interpretable and provides additional opportunities to reveal the patterns and structures within the systems of documents. Our methodology proved to be useful for this study, revealing the lexical cues generally applied by human reviewers to generate deceptive language.

Decision support tools have emerged as key technologies in data analysis enabling companies to make personalized offers to their customers with the help of data processing and data visualization tools. Embedded agents with conversational interface allow expressing queries in natural language in order to accelerate the report navigation. However the coverage, complexity and scale of such agents are much larger than simple query understanding. Moreover, most of them are often restricted to specific domain and explicit rules. In this paper, we present an approach which uses topic modeling and anomaly detection to point out the information that may be of particular interest to a domain expert. The strength of our approach is that it shows both domain and common sense knowledge and does not require the model to be re-trained for different experts. The proposed model can suggest decision options based on the analyzed data and user's activity. In particular, we propose an unsupervised method for automatic topic labeling, and show how it might be helpful in decision making. We also implement a framework, called MacNabbs, and give some results of our approach.

The challenging nature of error handling constantly escalates as a growing number of environments consists of networked devices and software components. In these environments, errors cover a uniquely large spectrum of situations related to each layer ranging from hardware to distributed platforms, to software components. Handling errors becomes a daunting task for programmers, whose outcome is unpredictable. Scaling up error handling requires to raise the level of abstraction beyond the code level and the try-catch construct, approaching error handling at the software architecture level.

Coordinating entities in a networked environment has always been a significant challenge for software developers. In recent years, however, it has become even more difficult, because devices have increasingly rich capabilities, combining an ever larger range of technologies (networking, multimedia, sensors, etc.).