Discovering common outcomes of agents’ communicative actions in various domains

摘要

We explore the common patterns of human behavior, expressed via communicative actions, and displayed in various domains of human activities associated with conflicts. We build the generic methodology based on machine learning and reasoning to predict specific communicative actions of human agents, given previous sequence of communicative actions of themselves and their opponents. This methodology is applied to textual as well as structured data on inter-human conflicts of diverse modalities. Scenarios are represented by directed graphs with labeled vertices (for communicative actions) and arcs (for temporal and causal relationships between subjects of these actions). Scenario representation and learning techniques are firstly developed in the domain of textual customer complaints, and then applied to such problems as predicting an outcome of international conflicts, assessment of an attitude of a security clearance candidate, mining emails for suspicious emotional profiles, and recognizing suspicious behavior of cell phone users. We present an evaluation of the proposed methodology in the domain of customer complaint and conduct some comparative evaluation in the other domains mentioned above. Successful use of the proposed methodology in rather distinct domains shows its adequacy for mining human attitude-related data in a wide range of applications.