Learning Structured Knowledge from Social Tagging Data: A Critical Review of Methods and Techniques

Abstract

For more than a decade, researchers have been proposing various methods and techniques to mine social tagging data and to learn structured knowledge. It is essential to conduct a comprehensive survey on the related work, which would benefit the research community by providing better understanding of the state-of-the-art and insights into the future research directions. The paper first defines the spectrum of Knowledge Organization Systems, from unstructured with less semantics to highly structured with richer semantics. It then reviews the related work by classifying the methods and techniques into two main categories, namely, learning term lists and learning relations. The method and techniques originated from natural language processing, data mining, machine learning, social network analysis, and the Semantic Web are discussed in detail under the two categories. We summarize the prominent issues with the current research and highlight future directions on learning constantly evolving knowledge from social media data.

Knowledge base enrichment by relation learning from social tagging data

“…However, tags have a flat structure without relations among them, which limits their usefulness in effective searching, navigation and recommendation. There have been many studies considering folksonomies as important sources for mining "collective intelligence" and deriving structured knowledge [17,21].…”

“…Many existing methods infer tag relations by exploiting the co-occurrence information as reviewed in [17,21], for example, through a heuristic based set inclusion measure [35,36] or graph centrality [26] in a tag-tag network. However, they simply ignore the meanings of tags, and it is difficult to formally interpret the meanings of the inferred relations.…”

Essay Scoring System Using Semantic Similarity Approach

“…These senses are the target labels of a classification problem. This algorithm distinguishes and removes the ambiguity of the words used in a concept (Dong, Wang, & Liang, 2015). Using WordNet, words are classified with glosses that identify the senses of a word according to its parts of speech resulted from POS tagging.…”

Analysis of the Feasibility of Using Data Obtained From Social Media to Build Ontologies: A Literature Review

“…Além disso, devido a natureza do contexto das redes sociais digitais, é possível extrair compreensões inéditas, como demonstrado nas pesquisas de Brambilla et al (2017) e Monachesi e Markus (2010). O processo de Folksonomia, conforme Dong et al (2015), é capaz de fornecer uma base semi-estruturada que pode ser estendida para a construção de um grafo de conhecimento. Devido à natureza imprevisível dos usuários, pode-se afirmar que os dados gerados de mídias sociais, sejam esses vídeos, imagens ou textos, são capazes de servir como base para a construção de ontologias se tratados corretamente, conforme visto nas pesquisas de Pereira et al (2018), Nechaev et al (2018), Wongthontham et al (2018, Suliman et al (2016) e Monachesi e Markus (2010).…”

“…se dedica a extrair entidades emergentes dado um domínio específico.Nechaev et al (2018) usam os dados das mídias sociais em conjunto com LOD para prever atributos de entidades, neste caso, o tipo de uma entidade.Pereira et al (2018) propõem analisar as menções de interesse de um dado conceito. Abu-Salih et al (2018) propõem a construção de um framework capaz de explorar domínios ontológicos, com o intuito de afirmar se um dado pertence ou não a um domínio.Thakker et al(2017) apresentam um modelo ontológico que é capaz de definir variações culturais, com os dados das mídias sociais como base teórica e a LOD como base empírica Dong et al (2015). apresentam uma revisão crítica que define o escopo do processo de categorização de Sistemas de Organização do conhecimento e analisa o processo de folksonomia, definido porDong et al (2015) como sistemas de marcação" social, do inglês "social tagging systems", para a extração de lista de termos e o aprendizado de relacionamentos.…”