Fatema Nafa

Conceptualize the Domain Knowledge Space in the Light of Cognitive Skills

In this paper, we propose an approach that can improve the quality of pedagogies based on Blooms Taxonomy (BT) cognitive theory. Theoretically, any domain knowledge can be learned and taught at multiple cognitive domain levels. Moreover, other cognitive domain levels might be called, for learn specific domain knowledge. If we know the dependencies between the domain knowledge, many interesting pedagogical applications are possible. However, until now, the relationship levels between domain knowledge are highly sophisticated and required tedious human judgment to be deduced. BT theory has been explored in the psychological sciences paradigm, but has not been examined automatically. No comprehensive computer science map is currently available. This paper, explores how the BT- relationships between various domain knowledge is automatically extracted. A Bloom Topic Graph (BTG) that encodes concept space is extracted. BTG provides concept space connected as BT cognitive relationships. Our approach utilizes verbs to discover the BT cognitive relationships between computer sciences, domain knowledge. We evaluate the BT cognitive relationships using ground truth, and our approach achieves an accuracy of average 65-75%, which is significantly high.

Discovering Bloom Taxonomic Relationships between Knowledge Units Using Semantic Graph Triangularity Mining

Inferring Blooms Taxonomy among knowledge units is important and challenging. This paper proposes a novel method that can identify the revised Blooms Taxonomy levels among knowledge units in the semantic cognitive graph (SCG) by using a graph triangularity. The method determines significant relationships among knowledge units by utilizing triangularity of knowledge units in the computer science domain. We share an experiment that evaluates and validates the method on three textbooks. The performance analysis shows that the method succeeds in discovering the hidden associations among knowledge units and classifying them.

Extending Cognitive Skill Classification of Common Verbs in the Domain of Computer Science for Algorithms Knowledge Units.

To provide an adaptive guidance to the instructors through designing an effective curriculum and associated learning objective, an automatic system needs to have a solid idea of the prerequisite cognitive skills that students have before commencing a new knowledge before enhancing those skills which will enable students to steadily acquire new skills. Obtaining the learning objectives in knowledge units based on cognitive skills is a tedious and time-consuming task. This paper presents subtasks of an automatic meta-learning recommended model that enables the extraction of learning objectives from knowledge units, which are teaching materials. Knowing the cognitive skills will help mentors to connect the knowledge gaps between learning materials and their aims. The model applies Natural Language Processing (NLP) techniques to identify relevant knowledge units and their verbs, which assist in the identification of extracting the learning objectives and classifying the verbs based on cognitive skill levels. This work focuses on the computer science knowledge domain. We share the result that evaluates and validates the model using three textbooks. The performance analysis shows the importance and the strength of the automatic extraction and classification of the verbs among knowledge units based on cognitive skills.

Mining Cognitive Skills Levels of Knowledge Units in Text Using Graph Tringluarity Mining

Semantic analysis among knowledge units in the text is a very interesting problem in numerous applications. Beside the semantic relationships expressed in the text, relationships are also encoded in knowledge structures in our brains. However, the relationships among knowledge units are highly sophisticated and require a human judgment. In this paper, we propose a Graph-Tringluarity-based system for knowledge units’ classification in the textual graph, which identifies the adapted Bloom’s Taxonomy levels. Given knowledge units, the system discovers significant relationship types among them based on the cognitive skills. We evaluate and validate the system on three datasets (textbooks) by utilizing the knowledge units of a computer science domain. As a result, the proposed system succeeds to discover the hidden associations among knowledge units and classify them. Furthermore, the performance shows expressive centrality measures of knowledge units’ analysis.

Does Location Matter? The Efficiency of Request Propagation Based on Location in Online Social Networks

The centrality metrics such as Closeness and Betweenness in Online Social Network (OSN) determine how much end-to-end delay and queue-load of a node can have as a source or as a destination through Social Routing. Experimentally, we find that nodes with high Out-Closeness centrality in OSN suffer from high end-to-end delay as a target, but not as a source. We show that the cause of this end-to-end delay is that most nodes with high Out-Closeness centrality have low In-Closeness centrality. Moreover, we show that the increase in the local In-Degree centrality will increase the global In-Closeness centrality. We also find that the promised level to increase the In-Closeness centrality of a node is its Friends of Friends-Of-Friends (Level-3). An agent-based Model for Social Routing is proposed and a set of large-scale Google+ Graphs are used. A simulation study is also completed by propagating a set of requests in different societies with different routing schemes and diverse queue disciplines, in order to compare the average end-to-end delays from the source and target perspectives.

Deepening Prose Comprehension by Incremental Free Text Conceptual Graph Mining and Knowledge

Deepening prose comprehension involves understanding the relation among the prose concepts and reading external references. In this paper, we propose an interesting system which mimics the human reading process. Given a prose, the system discovers the relevant parts from relevant references that connect and illuminate a set of learnable concepts from the prose by adding new familiarity meaningful knowledge paths among them. We present a computational evaluation model to measure the acquired knowledge and the prose learning process by the system. We present an experiment, which uses Wikipedia articles as an external reference consultations to comprehend prose. The performance analysis shows that the system succeeded in connecting the concepts by discovering the relation among them and increases the learning process on prose comprehension.

Connecting the Dots in a Concept Space by Iterative Reading of Freetext References with Wordnet

Most of the current text understanding techniques are based on ontology engine and external knowledge resources to reach to a deep comprehension. In this paper, we propose a computerized text comprehension technique for a given text. This technique can accommodate a deep text comprehension by an iterative reading of reference texts related to the given text using ontology engine. Performance analysis shows that the use of ontology engine and reference texts helps in finding the hidden relations among the concepts in the text and adds new knowledge. Thus, this iteratively increases the text comprehension.