Pooja Vashisth - Academia.edu (original) (raw)

Papers by Pooja Vashisth

Journal of Intelligent & Fuzzy Systems, 2017

2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2015

2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2013

Recommender Systems are a class of applications which are used to overcome the problem of informa... more Recommender Systems are a class of applications which are used to overcome the problem of information overload. They use the opinions of members of a community to help individuals in that community identify the information most likely to be interesting to them or relevant to their needs, by drawing on user preferences and filtering the set of possible options to a more manageable subset. The key element of such user-support systems is the user model. Traditional techniques used to create user models are usually too rigid to capture the inherent uncertainty of human behavior. Fuzzy sets can handle and process uncertainty in human decision-making and if used in user modeling can be of advantage as it will result in recommendations closely meeting user preferences. In this paper, a hybrid multi-agent recommender system is designed and developed where user's preferences; needs and satisfaction are modeled using interval type-2 (IT2) fuzzy sets. This results in improving the prediction accuracy of the system and hence better recommendations are generated. Experimental study was conducted on book recommender system and promising results were obtained.

Journal of Experimental & Theoretical Artificial Intelligence, 2014

ABSTRACT Recommender systems (RSs) use information filtering to recommend information of interest... more ABSTRACT Recommender systems (RSs) use information filtering to recommend information of interest (to a user). Similarly, personalisation can be adopted for recommendations in e-market. We propose a new and innovative system called as interest-based recommender system (IBRS) for personalisation of recommendations. The IBRS is an agent-based RS that takes into account user's preferences. It can transform a standard product (or service) into a dedicated solution for an individual. The system discovers interesting product alternatives based on user's underlying mental attitudes (likes and dislikes) during the repair process using argumentation. The proposed method combines a hybrid RS approach with automated argumentation-based reasoning between agents. The system improves results by improving the recommendation repair activity. We consider a book recommendation application, for experiment to carry out the system's (objective and subjective) evaluation using standard metrics. The experiments confirm that the proposed IBRS improves user's acceptance of the product as compared with a traditional hybrid method and an argumentation-enabled state-of-the-art recommendation method. The system has been found to be more effective than its traditional counterpart when dealing with the new user problems.

Managing Trust in Cyberspace, 2013

2011 International Conference on Communication Systems and Network Technologies, 2011

Interest-based-repair is a kind of Interest-Based Recommendation strategy that enhances recommend... more Interest-based-repair is a kind of Interest-Based Recommendation strategy that enhances recommendations. It allows automated user and recommender agents to ask for the implicit underlying goal (of seeking and providing recommendations). This leads to proposing repairs and alternative plan(s) which may entail an acceptance on alternative issues with higher satisfaction. Therefore, this paper (i) proposes a recommendation protocol that support both recommendations and interest-based repair using argumentation, (ii) various strategies used by a user and recommender agent, to generate interesting recommendations and (iii) a comparative analysis to show that how these strategies enhance recommendation technology.

Proceedings of the 2014 Recommender Systems Challenge on - RecSysChallenge '14, 2014

2012 12th International Conference on Intelligent Systems Design and Applications (ISDA), 2012

The goal of Recommender Systems (RSs) is to help users to deal with the problem of information ov... more The goal of Recommender Systems (RSs) is to help users to deal with the problem of information overload by facilitating access to relevant items that are valuable to them. If the recommended items match the user preferences, user trust in the system increases and the user start liking the system and uses it more frequently. Trust enabled Argumentation Based Recommender System (TABRS) designed and developed in this paper recommends items of interest to the user by using a hybrid approach for recommendation. These recommendations are further improved using argumentation to convince users about the product. TABRS is an agent-based recommender system that takes into account user's changing preferences to generate interesting recommendations. TABRS combines hybrid recommender system with automated argumentation between agents. The system also improves recommendation repair activity by discovering interesting alternatives based on user's underlying mental attitudes. We implemented the system using Jason for building agents enabled with inference and interaction capabilities. The experimental study is conducted for a Book Recommender System and performance of the proposed system is evaluated using precision and recall metrics.

2011 International Conference on Computational Intelligence and Communication Networks, 2011

... Punam Bedi, Pooja Vashisth Department of Computer Science University of Delhi Delhi, INDIA pu... more ... Punam Bedi, Pooja Vashisth Department of Computer Science University of Delhi Delhi, INDIA punambedi@ieee.org, poojavashisth@rediffmail.com ... II. UNDERLYING GOALS AND UTILITY OF APLAN Our aim here is to explore how exchanging meta-information about the ...

2011 World Congress on Information and Communication Technologies, 2011

The challenge in a recommendation system is to help users in dealing with the problem of informat... more The challenge in a recommendation system is to help users in dealing with the problem of information overload. Personalization, when applied to recommendation in e-market can transform a product into a dedicated solution for an individual. In this paper, we describe the method used for personalization of recommendations generated by an Interest-Based Recommender System (IBRS). This paper proposes a design

Information Sciences, 2014

Recommender systems (RSs) use the opinions of members of a community to help individuals in that ... more Recommender systems (RSs) use the opinions of members of a community to help individuals in that community identify the information most likely to be interesting to them or relevant to their needs. These systems use the similarity between the users and recommenders or between the items to form recommendation list for the user. We believe that, various interactions and arguments exchanged in favor or against are responsible for the eventual result of a recommendation process. Therefore, besides recommendations it is vital to determine the users' response on such interactions to determine more accurate trust estimates for users in the system. Hence, this paper proposes a novel fuzzy and argumentation based trust model which is also integrated within the practical reasoning of agents in the multi-agent recommender systems. This integration allows the agent to take trustworthy decisions and reason about them as well. The user is also able to make a wiser selection in case there are conflicting opinions related to a specific product or the user comes across a new, unseen product and is indecisive about it. As a result it improves recommender's persuasive power and user's trust in the system resulting in an increase in the user's acceptance of the recommendations. The experiments performed with a Book Recommender System (using a hybrid recommendation approach), confirms that the variant implemented with the proposed approach performs better than those using conventional methods. Results obtained from evaluation metrics showed that the recommendations were more accurate, relevant and novel.

Computational Intelligence and …, 2011

International Conference on Artificial Intelligence, 2010

... Location based E-Commerce in a Multi Agent Society Punam Bedi 1, Pooja Vashisth2 1Department ... more ... Location based E-Commerce in a Multi Agent Society Punam Bedi 1, Pooja Vashisth2 1Department of Computer Science, University of Delhi, Delhi, India 2 Department of Computer Science, University of Delhi, SPMC, Delhi, India ... start Any desires stop no yes Generate desires ...

Now days, there is an increasing level of interest in the application of argumentation within the... more Now days, there is an increasing level of interest in the application of argumentation within the artificial agent societies. This paper extends the operational semantics to speech-act based communication messages received by an AgentSpeak(L) agent in order to enable argumentation in cognitive agents. The aim is to give semantics and implementation as logic-based plans for some key illocutionary forces, used for argumentation in the Belief-Desire-Intention (BDI) agent communication language ‘AgentSpeak(L)’. The extension allows agents engaged in a dialogue to put forward their arguments, question beliefs of other agents more expressively. Therefore, using extended speech-act based communication; an agent can share its internal state with other agents and influence other agents’ states. This work also provides a new dimension to argumentation based negotiation in BDI agents as this would enable the agents to negotiate using argumentation. Argumentation based negotiation can provide a powerful tool for the agents communicating to fix a deal using the electronic commerce services.