Ontology modeling of semantics in social media:Public issue knowledge base (PIKB)of the Weibo

Purpose:This study aims to construct an ontology to model the semantics of social media streams,in particular,trending topics and public issues.Design/methodology/approach:Our knowledge base included 10 public events and topics from Weibo respectively,which were collected through keyword search and a crawler program.We used a semi-automatic approach to model and annotate the semantics in social media,and adapted the multi-layered ontology to refine the design based on previous researches,then we used named entity recognition(NER) to extract entities to instantiate the ontology.Relationships were extracted based on co-occurrence measures.Finally,we manually conducted post-filtering evaluation and edited the extracted entities and relationships.Findings:An initial assessment demonstrated that our multi-layered ontology supports various types of queries and analyses in the public issue knowledge base(PIKB),which can serve as an effective tool to query,understand and trace public issues.Research limitations:Manual involvement cannot meet the requirements for challenges of sustainable developments.Since the relationships extracted are fully based on the co-occurrence of entities,rich semantic relationships,such as how much the key players have been involved,could not be fully reflected.Besides,the user evaluation is necessary for further ontology assessment.Practical implications:The PIKB can be used by regular Web users and policy makers to query,understand,and make sense of public events and topics.The methodology and reusable ontology model are useful for institutions that are interested in making use of the social media data.Originality/value:In this study,a multi-layered ontology is applied to model the evolving semantics of public events and trending topics in social media,and the semi-automatic approach could make it possible to extract entities and relationships from large amount of unstructured short texts of user generated content(UGC) from social media.

Public＇s knowledge of the differences between ophthalmologists and optometrists：a critical issue in eye care service utilisation

AIM：To assess the public＇s knowledge of the differences between ophthalmologists and optometrists and identify the factors associated with knowledge.METHODS：The study was a population-based random survey of adults aged 18 years or older conducted in Enugu,south eastern Nigeria,between March and June,2011.Data on respondents＇ socio-demographics,clinical profile,and knowledge of the differences between ophthalmologists and optometrists were collected using a 28-item questionnaire.Data were analysed using descriptive and analytical statistics.Values of P〈0.05 were considered statistically significant.RESULTS：The respondents（P=394） comprised 198 males and 196 females（sex ratio =1.01：1）,aged 18-70（30.9 ±10.8） years.The majority of respondents were single（57.4%）,possessed secondary education（96.9%）,employed（65.2%） and had no health insurance（77.4%）.Their clinical profile showed previous eye exam 54.1%,spectacle wear 41.6%and contact lens wear 5.6%.In the multivariate analysis,participants＇ good knowledge of the differences between ophthalmologists and optometrists was significantly associated with educational status（OR：0.32,95%CI：0.23-0.44,P〈0.0001,β =-0.988）,employment status（OR：1.8,95%CI：1.45-2.25,P〈0.0001,β=0.124）and previous eye examination（OR：1.63,95%CI：1.29-2.07,P〈0.0001,β =0.549）.CONCLUSION：Participants＇ socio-demographic and clinical characteristics are important predictors of good knowledge.The findings may have implications for all stakeholders in eye care delivery.There is need for knowledge enhancement,by the government and eye care providers,through population-based eye health literacy campaigns.

A Three-Stage Knowledge Acquisition Method

This paper presents and analyzes three fundamental problems in knowledgeacquisition, and proposes a general method for tackling them. The methoddivides the whole process of knowledge acquisition into a set of almost indepen-dent pieces, each of which can be finished by knowledge engineers, experts andassistants, respectively.