Risk analysis and prediction in welfare institutions using a recommender system.Maayan Zhitomirsky-Geffet &Avital Zadok -2018 -AI and Society 33 (4):511-525.detailsRecommender systems are recently developed computer-assisted tools that support social and informational needs of various communities and help users exploit huge amounts of data for making optimal decisions. In this study, we present a new recommender system for assessment and risk prediction in child welfare institutions in Israel. The system exploits a large diachronic repository of manually completed questionnaires on functioning of welfare institutions and proposes two different rule-based computational models. The system accepts users’ requests via a simple graphical interface, (...) calculates the institutions’ profiles according to user preferences, and presents assessment scores, trends and comparative analyses of the corresponding data using assorted visual aids. Based on the analysis, the system offers three different strategies for objective assessment of the institutions’ functioning and risks. Qualitative and quantitative evaluation of the system’s effectiveness and accuracy demonstrates that it substantially improves the assessment process of a welfare institution. Moreover, it provides an effective tool for objective large-scale analysis of the institution’s overall state and trends, which were previously based primarily on the institution supervisors’ subjective judgment and intuition. In addition, the proposed recommender system has great practical and social impact as it may help identify and avert potential problems, malfunctions, flaws, risks and even tragic incidents in child welfare institutions, as well as increase their overall functioning levels. As a result, as a long-term social implication, the system may also help reduce inequality and social gaps in the Israeli society. (shrink)
A New Framework for Systematic Analysis and Classification of Inconsistencies in Multi-Viewpoint Ontologies.Golan Avidan &Maayan Zhitomirsky-Geffet -2022 -Knowledge Organization 48 (5):331-344.detailsPlurality of beliefs and theories in different knowledge domains calls for modelling multi-viewpoint ontologies and knowledge organization systems. A generic theoretical approach recently proposed for heterogeneity representation in KOS was linking each ontological statement to a specific validity scope to determine a set of conditions under which the statement is valid. However, the practical applicability of this approach has yet to be empirically assessed. In addition, there is still a need to investigate the types of inconsistencies that might arise in (...) multi-viewpoint ontologies as well as their possible causes. This study proposes a new framework for systematic analysis and classification of inconsistencies in multi-viewpoint ontologies. The framework is based on eight generic logical structures of ontological statements. To test the validity of the proposed framework, two ontologies from different knowledge domains were examined. We found that only three of the eight structures led to inconsistencies in both ontologies, while the other two structures were always present in logically consistent statements. The study has practical implications for building diversified and personalized knowledge systems. (shrink)
No categories
Utilizing Facebook for professional integration of three ethnic groups in Israel.Maayan Zhitomirsky-Geffet &Avraham Weic -2021 -AI and Society 36 (3):737-755.detailsThis study proposes a conceptual model for utilization of Facebook for professional integration of ethnic minorities, based on the social capital and weak social ties theories. In particular, the research focuses on differences among ethnic groups of Facebook users in their willingness to create intergroup work relations and its various influence factors. A designated questionnaire was composed and administered to 120 subjects from three ethnic groups in Israel: Jewish, Muslim-Arab and Druze. We found that the proportion of intergroup professional relations (...) was higher on Facebook than in the offline workspace in all three groups. There were numerous differences between the three examined groups: self-disclosure was significantly higher for Druze and Jewish users than for the Arab users, while the willingness to create intergroup professional connections was much higher for the two minorities than for the Jewish users. This study contributes to understanding the factors that influence social network behaviour of different ethnic groups. Our results indicate that social networking sites can catalyse creation of intergroup professional relations. Utilization of social networking sites as a platform for professional promotion might constitute a first step in the process of professional and cultural integration of minorities in the ethnically heterogeneous society. (shrink)