Sentiment Classification (SC) is about assigning a positive, negative or neutral label to a piece of text based on its overall opinion. This paper describes our in-progress work on extracting the meaning of words for SC. In particular, we investigate the utility of sense-level polarity information for SC. We first show that methods based on common classification features are not robust and their performance varies widely across different domains. We then show that sense-level polarity information features can significantly improve the performance of SC. We use datasets in different domains to study the robustness of the designated features. Our preliminary results show that the most common sense of the words result in the most robust results across different domains. In addition our observation shows that the sense-level polarity information is useful for producing a set of high-quality seed words which can be used for further improvement of SC task.

Robust methods for representing, generalizing, and sharing knowledge across various robotics systems and configurations are important in many domains of robotics research and application. In this paper we present a method for modeling tasks and robot skills to simplify the programming and reuse of knowledge between robots in manufacturing environments. Specifically, we propose an assembly taxonomy designed to represent the decomposition of high-level, complex assembly tasks into simple skills and skill primitives that the robot must use in a specified sequence. By using programming by demonstration to populate the taxonomy, we propose a method to easily interact with and reuse knowledge in various manufacturing robotics systems, making it possible to reduce programming time and overhead. We present both a detailed discussion of this taxonomy, as well as an example of how the taxonomy can be applied to an assembly task.

Interest in online education is surging, as dramatized bythe success of Khan Academy and recent Stanford online courses, but the technology for online education isin its infancy. Crowdsourcing mechanisms will likelybe essential in order to reach the full potential of thismedium. This paper sketches some of the challengesand directions we hope HCOMP researchers will address.

Collision avoidance and multi-agent navigation is an important component of modern video games. Recent developments in commodity hardware, in particular the utilization of multi-core and many-core architectures in personal computers and consoles are allowing large numbers of virtual agents to be incorporated into game levels in increasing numbers. We present the hybrid reciprocal velocity obstacle and optimal reciprocal collision avoidance methods for reciprocal collision avoidance and navigation in video games and described their implementations in C++ as HRVO Library and RVO2 Library. The libraries can efficiently simulate groups of twenty-five to one thousand virtual agents in dense conditions and around moving and static obstacles.

In this paper, we develop some new Captchas belonging to genre – "CAPTCHAs with a purpose". These CAPTCHAs apart from having its applications serve some useful purpose. reCAPTCHA is one such Captcha developed at Carnegie Mellon University. It helps to digitize books. Another such Captcha is Asirra developed at Microsoft which provides homes for homeless animals. In this paper, we present Time based, Sentence based, Human Emotion based CAPTCHAs which have range of other useful purpose such as measuring reaction time of people, promoting news, general knowledge facts, jokes among people while engaging in routine activities such as checking email. Also, one can be used for conducting online polls on a very large scale. We also showcase a New Game with a Purpose called "Identical Emotions" which helps to assign tags describing emotions depicted by the images, to varied images. It can also be used to serve Emotion Based CAPTCHA. We also present a new scheme which renders attack on CAPTCHAs useless and make old CAPTCHAs reusable and help in using CAPTCHAs which might serve some practical purpose which otherwise might be vulnerable to use. This system also enables to use different "CAPTCHAs with a purpose" in conjunction with each other. At present most websites deploy only a single algorithm reCAPTCHA whose practical purpose is to digitize books, thus is limited to one domain. This system can thus, broaden the application domain of CAPTCHAs.

We discuss preliminary work focusing on the problem of combining social interaction with task-based action in a dynamic, multiagent bartending domain, using an embodied robot. We show how the users' spoken input is interpreted, discuss how social states are inferred from the parsed speech together with low-level information from the vision system, and present a planning approach that models task, dialogue, and social actions in a simple bartending scenario. This approach allows us to build interesting plans, which have been evaluated in a real-world study, using a general purpose, off-the-shelf planner, as an alternative to more mainstream methods of interaction management.

The most critical moves that determine the success of a manipulation task are performed within the close vicinities of the object prior to grasping, and the goal prior to the final placement. Memorizing these state-action sequences and reusing them can dramatically improve the task efficiency, whereas even the state-of-the-art planning algorithms may require significant amount of time and computational resources to generate a solution from scratch depending on the complexity and the constraints of the task. In this paper, we propose a hybrid approach that combines the reliability of the past experiences gained through demonstration and the flexibility of a generative motion planning algorithm, namely RRT*, to improve task execution efficiency. As a side benefit of reusing these final moves, we can dramatically reduce the number of nodes used by the generative planner, hence the planning time, by either early-terminating the planner when the generated plan reaches a "recalled state", or deliberately biasing it towards the memorized state-action sequences that are feasible at the moment. This complementary combination of the already available partial plans and the generated ones yield to fast, reliable, and repeatable solutions.

A general consensus on representation of emotions and feelings in cognitive architectures is currently missing; yet artificial emotional intelligence is vital for the integration of future robots into the human society. This work introduces one possible approach to representation and processing of emotional mental states and attitudes, that allows for implementation of control of agent behavior by emotions as well as for recognition of emotional motivations in another agent's behavior. One particular advantage of this approach is that it allows for representation and processing of complex/social emotional attitudes, like shame, jealousy, resentment, or humor. The proposed validation of the approach is based on simulation of the emergence of emotional relationships in a small group of agents in a virtual environment.

People complete tasks more quickly when they have concrete plans, especially for open-ended, creative tasks. However, people often fail to create such action plans. (How) can systems provide people with these concrete steps automatically? To scalably provide personalized action plans, this paper introduces and evaluates crowdsourcing and peer approaches for creating plans, and NLP techniques for reusing them. We evaluated the effects of action plans on different types of tasks. A between-subjects experiment found that people who received crowd-created plans completed more tasks than people asked to self-create plans and than a control group without action plans. We found that crowd-created action plans are especially effective for lingering and high-level tasks. A second experiment found that peer-provided plans led to more completed tasks than no plans. A third experiment found that participants who received reused action plans also completed more tasks than a control group without action plans. We have incorporated these principles into TaskGenies: a crowd-powered task management system.

It is well established that in certain domains, noisy inputs can be reliablycombined to obtain a better answer than any individual.It is now possible to consider the crowdsourcing of physical actions,commonly used for creative expressions such as drawing, shading, and singing.We provide algorithms for converting low-quality inputobtained from the physical actions of a crowd into high-quality output.The inputs take the form of line drawings, shaded images, and songs.We investigate single-individual crowds (multiple inputs from a single human)and multiple-individual crowds.