Comparing measures of semantic similarity

Ljubešić, Nikola; Boras, Damir; Bakarić, Nikola; Njavro, J.

doi:10.1109/iti.2008.4588492

Cited by 20 publications

(15 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In order to compute the similarity of the diseases in each pair, the diseases were expressed as a vector of symptom concepts. For our experiment, we chose the following similarity measures, which are the main ones used in the literature [17]:…”

Section: B Evaluationmentioning

confidence: 99%

Evaluating Wikipedia as a Source of Information for Disease Understanding

Valle

García

Santamaría

et al. 2018

2018 IEEE 31st International Symposium on Computer-Based Medical Systems (CBMS)

View full text Add to dashboard Cite

The increasing availability of biological data is improving our understanding of diseases and providing new insight into their underlying relationships. Thanks to the improvements on both text mining techniques and computational capacity, the combination of biological data with semantic information obtained from medical publications has proven to be a very promising path. However, the limitations in the access to these data and their lack of structure pose challenges to this approach. In this document we propose the use of Wikipedia -the free online encyclopedia -as a source of accessible textual information for disease understanding research. To check its validity, we compare its performance in the determination of relationships between diseases with that of PubMed, one of the most consulted data sources of medical texts. The obtained results suggest that the information extracted from Wikipedia is as relevant as that obtained from PubMed abstracts (i.e. the free access portion of its articles), although further research is proposed to verify its reliability for medical studies.

show abstract

Section: B Evaluationmentioning

confidence: 99%

Evaluating Wikipedia as a Source of Information for Disease Understanding

Valle

García

Santamaría

et al. 2018

2018 IEEE 31st International Symposium on Computer-Based Medical Systems (CBMS)

View full text Add to dashboard Cite

show abstract

“…To do this, we opted for the Jaccad index [41]. The Jaccard similarity measure is defined by the quotient of the number of common objects by the total number of objects from which is subtracted the number of common objects:…”

Section: Computing Of the Disorientation Indicatormentioning

confidence: 99%

A Semantic Analysis of the Learner’s Disorientation

Adda¹,

Bousbia²,

Balla³

2016

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

Abstract-Learning systems are dedicated for learning about a particular area organized through non-linear documents. Therefore, it is always useful to recognize the state of knowledge and the navigation behaviour of a learner in order to evaluate customize and adapt the learning process. In this paper, we aim to make a semantic analysis of the learner's navigation during his apprenticeship in hypermedia content. The main reason of this analysis is to identify the browsing behaviour of a learner with the current course. We assume that if the semantic distance between the domain concepts of the documents (or pages) that follow each other in the navigation of a learner is great, then this reflects the unstructured navigation behaviour and interprets that the learner is disoriented. This type of behaviour could be due to the poor organization of the content and the bad structuring of the course. Indeed, this analysis will allow to the tutor, to identify the disoriented learners and help them, and to the course author, to specify the causes to restructure and to deepen the analysis of the existing content and the navigation links between the parts of the course.

show abstract

“…At this point of the procedure, in order to determine if two tags are related, the dissimilarity between their corresponding empirical co-occurrence probability distributions must be computed. In the literature, the Jensen-Shannon Divergence (JSD) [15] is a widely used metrics which has shown to outperform other measures [19]. It is based on Kullback-Leibler Divergence (KLD) [20], however, it is symmetric and has always a finite value.…”

Section: Dissimilarity Metricsmentioning

confidence: 99%

Tag relatedness in image folksonomies

Sergieh¹,

Egyed-Zsigmond²,

Gianini³

et al. 2014

Document numérique

View full text Add to dashboard Cite

Folksonomies-networks of users, resources, and tags-allow users to retrieve, organize and browse web contents. However, their advantages are limited mainly due to the noisiness of user provided tags. To overcome this issue, we propose an approach for characterizing related tags in folksonomies: we use tag co-occurrence statistics and Laplacian Score based feature selection in order to create empirical co-occurrence probability distribution for each tag; then we identify related tags on the basis of the dissimilarity between their distributions. To this purpose we introduce variant of the Jensen-Shannon Divergence, which is more robust to statistical noise. We experimentally evaluate our approach by using Word-Net and compare it to a common tag-relatedness approach based on the cosine similarity. The results show the advantage of our approach over the competing method.

show abstract

Comparing measures of semantic similarity

Cited by 20 publications

References 6 publications

Evaluating Wikipedia as a Source of Information for Disease Understanding

Evaluating Wikipedia as a Source of Information for Disease Understanding

A Semantic Analysis of the Learner’s Disorientation

Tag relatedness in image folksonomies

Contact Info

Product

Resources

About