Human social learning is an effective process that has inspired many existing machine learning approaches, such as learning from observation and learning by demonstration . In this paper, we introduce another form of social learning, learning from a casual conversation or LCC a machine learning approach in which an artificially intelligent agent learns new information through an extended natural language dialog with a human. Our system enables the agent to add or change information in its knowledge base as a result of the human’s conversational text inputs. LCC seeks to close an important gap in the state of the art that has focused on teaching computer agents how to perform specific tasks. Furthermore, LCC could also provide an efficient way to enhance the knowledge base of certain types of systems without requiring the involvement of a programmer. LCC does not require the user to enter specific information; instead, the user can converse naturally with the agent. As part of its learning process, LCC identifies the text inputs from the conversing human that contain information worth learning, and then determines whether the inputs are heretofore unknown and learns it; in agreement with what it already “knows” and ignores it; or in conflict with what it “knows” and it must resolve the conflict. LCC’s architecture consists of multiple sub-systems combined to perform the above tasks. Its learning component can add new information to the knowledge base, confirm existing information, and/or update existing information found to be related to the user input. The LCC system functionality was rigorously assessed with test statements comprising various difficulty levels. Furthermore, its acceptance by human users was evaluated by two separate groups of human test subjects—one group who interacted with the system, and a second group that evaluated the logs of the interactions of the first group. The collected results were all found to be acceptable and within the range of our expectations.

An application area of increasing importance is creating agent-based simulations to model human societies. One component of developing these simulations is the ability to generate realistic human social networks. Online social networking websites, such as Facebook, Google+, and Twitter, have increased in popularity in the last decade. Despite the increase in online social networking tools and the importance of studying human behavior in these networks, collecting data directly from these networks is not always feasible due to privacy concerns. Previous work in this area has primarily been limited to 1) network generators that aim to duplicate a small subset of the original network’s properties and 2) problem-specific generators for applications such as the evaluation of community detection algorithms. In this thesis, we extended two synthetic network generators to enable them to duplicate the properties of a specific dataset. In the first generator, we consider feature similarity and label homophily among individuals when forming links. The second generator is designed to handle multiplex networks that contain different link types. We evaluate the performance of both generators on existing real-world social network datasets, as well as comparing our methods with a related synthetic network generator. In this thesis, we demonstrate that the proposed synthetic network generators are both time efficient and require only limited parameter optimization. .

Over the past few years, the importance of having realistic conversational systems that satisfy the user needs have encouraged researchers to investigate new approaches for intelligent systems that are able to handle the required dialogues. However, designing a realistic conversational system that is able to understand the nuances of human conversation is not an easy task; thus, researchers face several challenges. To address these challenges and to help guide future research, we provide in this paper an overview of the most recent works in conversational systems. We classify the current models based on their functional similarities to address common features among the described systems. We also summarize the methods and approaches used by each system, state the systems limitations, and highlight their strengths.

Cryptography is the field of science which aims to construct systems that can withstand any abuse. The systems are designed in such a way that, even under malicious attacks, the systems can perform their functionalities without any security issues and without revealing any secret information [Goldreich 2004]. Cryptography has been an important field even centuries before modern computers. However, after widespread usage of Internet, it has become an important aspect of our daily life, because personal information such as user names, passwords, credit card information etc. which are required to use modern systems needs to be secure. In this research, we surveyed several papers ranging from classical to more recent ones which become milestones in this field. This paper basically addresses fundamental techniques that have been used in this field, and their applications.

In many cases, creating long-term solutions to sustainability issues requires not only innovative technology, but also large-scale public adoption of the proposed solutions. Social simulations are a valuable but underutilized tool that can help public policy researchers understand when sustainable practices are likely to make the delicate transition from being an individual choice to becoming a social norm. In this paper, we introduce a new normative multi-agent architecture, Cognitive Social Learners (CSL), that models bottom-up norm emergence through a social learning mechanism, while using BDI (Belief/Desire/Intention) reasoning to handle adoption and compliance. CSL preserves a greater sense of cognitive realism than influence propagation or infectious transmission approaches, enabling the modeling of complex beliefs and contradictory objectives within an agent-based simulation. In this paper, we demonstrate the use of CSL for modeling norm emergence of recycling practices and public participation in a smoke-free campus initiative.

Synthetic social network generators are useful for a variety of purposes, including benchmarking algorithms, modeling human interactions within agent-based simulations, and debugging code. Despite the increased availability of social media data, collecting data directly from these networks is not always feasible due to privacy concerns. Often data access is restricted to “silos” of analysts with privileged access. Lack of access to the original dataset increases the challenge of debugging the network analysis software. To combat this problem, this paper introduces a multi-purpose synthetic network generator designed for cloning the network statistics of an existing dataset. Our network generator supports the synthetic generation of two properties commonly present in real-world networks: node features and multiple link types. We describe common usage cases for our software and provide an evaluation on its performance on recreating the original network.