Biblio

As many organizations deploy their chatbots on social network applications to interact with their customers, a person may switch among different chatbots for different services. To reduce the switching cost, this study proposed the Federated Chat Service Framework. The framework maintains user profiles and historical behaviors. Instead of deploying chatbots, organizations follow the rules of the framework to provide chat services. Therefore, the framework can organize service requests with context information and responses to emulate the conversations between users and chat services. Consequently, the study can hopefully contribute to reducing the cost for a user to communicate with different chatbots.

The proliferation of mobile technology promotes social activities without time and space limitation. Users share information about their interests and preferences through a social network service, blog, or community. However, sensitive personal information may be exposed with the use of social activities. For example, a specific person can be identified according to exposure of personal information on the web. In this paper, we shows that a nickname that is used in an online community can be tracked by analysis of a user's behavior even though the nickname is changed to avoid identification. Unlike existing studies about user identification in a social network service, we focus on online community, which has not been extensively studied. We analyze characteristics of the online community and propose a method to track a user's nickname change to identify the user. We validate the proposed method using data collected from the online community. Results show that the proposed method can track the user's nickname change and link the old nickname with the new one.

This paper proposes and describes an active authentication model based on user profiles built from user-issued commands when interacting with GUI-based application. Previous behavioral models derived from user issued commands were limited to analyzing the user's interaction with the *Nix (Linux or Unix) command shell program. Human-computer interaction (HCI) research has explored the idea of building users profiles based on their behavioral patterns when interacting with such graphical interfaces. It did so by analyzing the user's keystroke and/or mouse dynamics. However, none had explored the idea of creating profiles by capturing users' usage characteristics when interacting with a specific application beyond how a user strikes the keyboard or moves the mouse across the screen. We obtain and utilize a dataset of user command streams collected from working with Microsoft (MS) Word to serve as a test bed. User profiles are first built using MS Word commands and identification takes place using machine learning algorithms. Best performance in terms of both accuracy and Area under the Curve (AUC) for Receiver Operating Characteristic (ROC) curve is reported using Random Forests (RF) and AdaBoost with random forests.