Ontology-driven web-based semantic similarity

Sánchez, David; Batet, Montserrat; Valls, Aïda; Gibert, Karina

doi:10.1007/s10844-009-0103-x

Cited by 71 publications

(44 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This argument that has been supported by recent works on privacy-protection (Chow, Golle, & Staddon, 2008;Sánchez, et al, 2013a;Sánchez, Batet, & Viejo, 2013b), which considered the Web as a realistic proxy of social knowledge. In order to compute term probabilities from the Web in an efficient manner, several authors (Sánchez, Batet, Valls, & Gibert, 2010;Turney, 2001) have used the hit count returned by a Web Search Engine (e.g., Bing, Google) when querying the term t. In our approach, term probabilities are computed in this way:…”

Section: Step-0: Defining the User's Personal Privacy Requirementsmentioning

confidence: 99%

REMOVED: Enforcing transparent access to private content in social networks by means of automatic sanitization

Viejo

Sánchez

2015

Expert Systems with Applications

Self Cite

View full text Add to dashboard Cite

Section: Step-0: Defining the User's Personal Privacy Requirementsmentioning

confidence: 99%

REMOVED: Enforcing transparent access to private content in social networks by means of automatic sanitization

Viejo

Sánchez

2015

Expert Systems with Applications

Self Cite

View full text Add to dashboard Cite

“…According to the theories of knowledge base modeling and manipulation technology, KBS can be categorized as linguistic knowledge bases (Baker, 2014;Fellbaum, 1998;Speer & Havasi, 2012), expert knowledge bases (Driankov, Hellendoorn, & Reinfrank, 2013;Kerr-Wilson & Pedrycz, 2016;Kung & Su, 2007), ontology (Fensel, 2004;Sanchez, Batet, Valls, & Gibert, 2010) and most recently the cognitive knowledge base (Wang, 2014).…”

Section: Knowledge Base Modeling Approachesmentioning

confidence: 99%

A Cognitive Knowledge-based Framework for Social and Metacognitive Support in Mobile Learning

Al-Hunaiyyan

Bimba

Idris

et al. 2017

IJIKM

View full text Add to dashboard Cite

Aim/Purpose: This work aims to present a knowledge modeling technique that supports the representation of the student learning process and that is capable of providing a means for self-assessment and evaluating newly acquired knowledge. The objective is to propose a means to address the pedagogical challenges in m-learning by aiding students’ metacognition through a model of a student with the target domain and pedagogy. Background: This research proposes a framework for social and meta-cognitive support to tackle the challenges raised. Two algorithms are introduced: the meta-cognition algorithm for representing the student’s learning process, which is capable of providing a means for self-assessment, and the social group mapping algorithm for classifying students according to social groups. Methodology : Based on the characteristics of knowledge in an m-learning system, the cognitive knowledge base is proposed for knowledge elicitation and representation. The proposed technique allows a proper categorization of students to support collaborative learning in a social platform by utilizing the strength of m-learning in a social context. The social group mapping and metacognition algorithms are presented. Contribution: The proposed model is envisaged to serve as a guide for developers in implementing suitable m-learning applications. Furthermore, educationists and instructors can devise new pedagogical practices based on the possibilities provided by the proposed m-learning framework. Findings: The effectiveness of any knowledge management system is grounded in the technique used in representing the knowledge. The CKB proposed manipulates knowledge as a dynamic concept network, similar to human knowledge processing, thus, providing a rich semantic capability, which provides various relationships between concepts. Recommendations for Practitioners: Educationist and instructors need to develop new pedagogical practices in line with m-learning. Recommendation for Researchers: The design and implementation of an effective m-learning application are challenging due to the reliance on both pedagogical and technological elements. To tackle this challenge, frameworks which describe the conceptual interaction between the various components of pedagogy and technology need to be proposed. Impact on Society: The creation of an educational platform that provides instant access to relevant knowledge. Future Research: In the future, the proposed framework will be evaluated against some set of criteria for its effectiveness in acquiring and presenting knowledge in a real-life scenario. By analyzing real student interaction in m-learning, the algorithms will be tested to show their applicability in eliciting student metacognition and support for social interactivity.

show abstract

“…Only Nandi & Bernstein have proposed a technique which was based on logs from virtual shops for computing similarity between products [26]. However, a number of works have addressed the semantic similarity measurement [16], [28], [30], [34], [35], and the use of WI techniques for solving computational problems [19], [36], [37] separately.…”

Section: Related Workmentioning

confidence: 99%

Semantic similarity measurement using historical google search patterns

Martinez‐Gil

Aldana‐Montes

2013

Inf Syst Front

View full text Add to dashboard Cite

Computing the similarity between terms (or short text expressions) that have the same meaning but which are not lexicographically similar is a key challenge in the information integration field. The problem is that techniques for textual semantic similarity measurement often fail to deal with words not covered by synonym dictionaries. In this paper, we try to solve this problem by determining the semantic similarity for terms using the knowledge inherent in the search history logs from the Google search engine. To do that, we have designed and evaluated four algorithmic methods for measuring the semantic similarity between terms using their associated history search patterns. These algorithmic methods are: a) frequent co-occurrence of terms in search patterns, b) computation of the relationship between search patterns, c) outlier coincidence on search patterns, and d) forecasting comparisons. We have shown experimentally that some of these methods correlate well with respect to human judgment when evaluating general purpose benchmark datasets, and significantly outperform existing methods when evaluating datasets containing terms that do not usually appear in dictionaries.

show abstract

Ontology-driven web-based semantic similarity

Cited by 71 publications

References 28 publications

REMOVED: Enforcing transparent access to private content in social networks by means of automatic sanitization

REMOVED: Enforcing transparent access to private content in social networks by means of automatic sanitization

A Cognitive Knowledge-based Framework for Social and Metacognitive Support in Mobile Learning

Semantic similarity measurement using historical google search patterns

Contact Info

Product

Resources

About