A concept-based model for enhancing text categorization

Shehata, Shady; Karray, Fakhri; Kamel, Mohamed S.

doi:10.1145/1281192.1281260

Cited by 51 publications

(23 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second component constructs a conceptual ontological graph (COG) to describe the semantic structures and the last component extract top concepts based on the first two components to build feature vectors using the standard vector space model. Concept-based model can effectively discriminate between non important terms and meaningful terms which describe a sentence meaning [8]. The concept-based model usually relies upon natural language processing techniques.…”

Section: Concept Based Methodsmentioning

confidence: 99%

Text Mining Methods and Techniques

Gaikwad¹,

Chaugule²,

Patil³

2014

IJCA

106

View full text Add to dashboard Cite

In recent years growth of digital data is increasing, knowledge discovery and data mining have attracted great attention with coming up need for turning such data into useful information and knowledge. The use of the information and knowledge extracted from a large amount of data benefits many applications like market analysis and business management. In many applications database stores information in text form so text mining is the one of the most resent area for research. To extract user required information is the challenging issue. Text Mining is an important step of knowledge discovery process. Text mining extracts hidden information from notstructured to semi-structured data. Text mining is the discovery by automatically extracting information from different written resources and also by computer for extracting new, previously unknown information. This survey paper tries to cover the text mining techniques and methods that solve these challenges. In this survey paper we discuss such successful techniques and methods to give effectiveness over information retrieval in text mining. The types of situations where each technology may be useful in order to help users are also discussed.

show abstract

Section: Concept Based Methodsmentioning

confidence: 99%

Text Mining Methods and Techniques

Gaikwad¹,

Chaugule²,

Patil³

2014

IJCA

106

View full text Add to dashboard Cite

show abstract

“…These parameters are used in the evaluation of ontologies (e.g., Khan et al 2004;Nagypal 2005;Shehata et al 2007, Lemnitzer et al 2008) and discussed in detail in Kaya and Altun (2011). Precision is the rate of retrieved document count to total document count (1), and recall is the rate of retrieved relevant document count to total relevant document count either retrieved or cannot be retrieved (2).…”

Section: Effectiveness Analysismentioning

confidence: 99%

Development and Evaluation of an Ontology Based Navigation Tool with Learning Objects for Educational Purposes

Altun

Kaya

2014

The New Development of Technology Enhanced Learning

View full text Add to dashboard Cite

Learning objects offer a new content design methodology for instructional designers in developing and utilizing e-learning environments. These learning objects are usually tagged and stored in repositories in a taxonomic way and mostly accompanied by key-based searching capability. Since those repositories do not have complicated reasoning and inference capabilities, access to and integration of them into an existing course package create a problem for e-learning instructors and learners. These problems will be able to be fixed by integration of semantic web technologies, and current learning object repositories could better be utilized by developing ontology-based learning object retrieval tools. In this chapter, the development and evaluation of an ontology-based learning object navigation and retrieval tool (OBELON) is presented. As part of an evaluation process, OBELON was compared with a taxonomy-based learning object retrieval system by using two information retrieval parameters: precision and recall. The findings indicated that ontology-based system produced more precise and high recall scores.

show abstract

“…Finally, the semantic structure of sentence has been applied in a few text mining applications. In text categorization, Shehata et al [25] propose conceptual term frequency as a new term weight scheme computing at sentence semantic level. Our motivation to measure sentence similarity at sentence semantic level is similar to [29].…”

Section: Related Workmentioning

confidence: 99%

“…The relevance score between the sentence and query is derived from a cosine similarity between conceptual term frequency (CTF) weighted vectors of a sentence and CTFweighted vector of a given query. In this work, we adopt Shehata et al's formulation of CTF [25], in which a CTF of term i in sentence j is computed as a linear combination of its normalized term frequency and normalized conceptual term frequency. We assign single-word tokens as the conceptual term features and compute CTF i weight for each conceptual term feature i.…”

Section: Sentence Retrievalmentioning

confidence: 99%