Hazra Imran

PLORS: a personalized learning object recommender system

Learning management systems (LMS) are typically used by large educational institutions and focus on supporting instructors in managing and administrating online courses. However, such LMS typically use a “one size fits all” approach without considering individual learner’s profile. A learner’s profile can, for example, consists of his/her learning styles, goals, prior knowledge, abilities, and interests. Generally, LMSs do not cater individual learners’ needs based on their profile. However, considering learners’ profiles can help in enhancing the learning experiences and performance of learners within the course. To support personalization in LMS, recommender systems can be used to recommend appropriate learning objects to learners to increase their learning. In this paper, we introduce the personalized learning object recommender system. The proposed system supports learners by providing them recommendations about which learning objects within the course are more useful for them, considering the learning object they are visiting as well as the learning objects visited by other learners with similar profiles. This kind of personalization can help in improving the overall quality of learning by providing recommendations of learning objects that are useful but were overlooked or intentionally skipped by learners. Such recommendations can increase learners’ performance and satisfaction during the course.

Co-occurrence based predictors for estimating query difficulty

Query difficulty prediction aims to identify, in advance, how reliably an information retrieval system will perform when faced with a particular user request. The prediction of query difficulty level is an interesting and important issue in Information Retrieval (IR) and is still an open research. In order to appreciate importance of query difficulty prediction we present an example., Information Retrieval (IR) is the Science of searching the relevant documents based on user’s need and a way towards discovering knowledge from text data. User’s needs are often expressed in terms of query. It has been observed that there is a word mismatch problem while matching user’s query to the documents. This is because users and authors of documents do not use same vocabulary. Query expansion/reformulation is a method to overcome such mismatch in terminology. Query expansion (QE) has become a well known technique that has been shown to improve average retrieval performance. However despite extensive research QE does not provide consistent gains over different query sets and collections. Therefore this technique has not been used in many operational systems as it may degrade performance of individual queries. A thorough investigation into robustness of query expansion is required in order to ensure reliability of query expansion for individual queries. It is well-known in the Information Retrieval community that methods such as query expansion can help ”easy” queries but are detrimental to ”hard” queries If the performance of queries can be predicted before retrieval then specific measures can be taken to improve the overall performance of the system. In this paper we do thorough investigations of various query difficulty predictors l and suggest two new query predictorsl based on co-occurrence of query terms. To evaluate the predictors, we have experimented on standard TREC collections. Our work is significant as it is a step towards judging reliability and robustness of query processing operations such as query expansion.

Toward Recommending Learning Tasks in a Learner-Centered Approach

Learner-centered education becomes more and more popular. One way of offering learner-centered education is to have assignments where learners can select from a pool of learning tasks with different difficulty levels (e.g., many easy tasks, few challenging tasks, etc.). However, a problem that learners can face in such assignments is to select the tasks that are most appropriate for them. In this paper, we introduce a rule-based recommender system that supports learners in selecting learning tasks. Such recommendations aim at helping learners to select the tasks from which they can benefit most in terms of maximizing their learning.

A Rule-Based Recommender System to Suggest Learning Tasks

Learner-centered learning can be defined as an approach to learning in which learners choose the topic to study and learning tasks. Because of available choices, learners can find it difficult to make a decision about which of the topics/tasks would be more appropriate for them. Identifying other learners with similar characteristics and then considering the tasks that worked well, makes it possible to suggest appropriate tasks to a learner. Based on this concept, we introduce a rule-based recommender system that supports learner-centered learning and helps learners to select learning tasks that are most suitable for them, with the focus on maximizing their learning.

VAT-RUBARS: A Visualization and Analytical Tool for a Rule-Based Recommender System to Support Teachers in a Learner-Centered Learning Approach

Smart learning environments are technology-enhanced educational systems that not only support learners’ learning but also provide a learning environment to learners according to their learning needs. In our previous research, we proposed a rule-based recommender system that supports learners in a learner-centered approach (Imran et al. A rule-based recommender system to suggest learning tasks. Springer, Honolulu, 2014). In this chapter, we introduce a visualization and analytical tool for rule-based recommender system (VAT-RUBARS) to provide support to teachers in learner-centered courses. As a result, teachers no longer need to make assumptions about their learners (or courses) and can improve the learning environment to make it more smart and productive for their learners.

Genetic Algorithm Based Model for Effective Document Retrieval

One central problem of information retrieval is to determine the relevance of documents with respect to the user information needs. The choice of similarity measure is crucial for improving search effectiveness of a retrieval system. Different similarity measures have been suggested to match the query and documents. Some of the popular measures being: cosine, jaccard, dice, okapi etc., each having their own pros and cons. Accordingly one may give better result over other depending on users need, document corpus, organization and indexing of corpus. Therefore it may be justifiable to combine these measures and develop a new similarity measure which can be named as combined similarity measure. Now individual measures can be assigned weights in different proportion in combined similarity measure. In order to optimize ranking of relevant documents, individual weights have to be optimized. In this chapter we suggest a genetic algorithm based model for learning weights of individual components of combined similarity measure. We have considered two different types of functions viz: non-order based and order based fitness functions to evaluate the goodness of the solution. A non-order based fitness function is based on recall-precision values only. However, it has been observed that a better fitness function can be obtained if we also consider the order in which relevant documents are retrieved. This leads to an idea of order based fitness functions. We evaluated the efficacy of a genetic algorithm with various fitness functions. The experiments have been carried out on TREC data collection. The results have been compared with various well-known similarity measures.

A framework for automatic query expansion

The objective of this paper is to provide a framework and computational model for automatic query expansion using psuedo relevance feedback. We expect that our model can be helpful in dealing with many important aspects in automatic query expansion in an efficient way. We have performed experiments based on our model using TREC data set. Results are encouraging as they indicate improvement in retrieval efficiency after applying query expansion.

A Trainable Document Summarizer Using Bayesian Classifier Approach

This paper presents an investigation into machine learning approach for document summarization. A major challenge related to document summarization is selection of features and learning patterns of these features which determines what information in source should be included in the summary. Instead of selecting and combining these features in ad hoc manner which would require readjustment for each new genre, natural choice is to use machine learning techniques. This is the basis for trainable machine learning approach to summarization. We briefly discuss design, implementation and performance of Bayesian classifier approach for document summarization.

Modular Neural Network Learning Using Fuzzy Temporal Database

Despite the availability of several well-known neural network learning algorithms, we have taken the initiative to propose a new mechanism for initial learning and training of a neural network. Our methodology uses fuzzy temporal database as a storehouse of information that would be used to feed the network for learning and perfecting itself.