Publications with Fulltext

Permanent URI for this collectionhttps://hdl.handle.net/20.500.14288/6

Browse

Filters

20212

Advanced Search

Filter by

Settings

Department: search.filters.department.Department of SociologySubject: search.filters.subject.Psychology

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationOpen Access
    Random sampling in corpus design: cross-context generalizability in automated multicountry protest event collection
    (Sage, 2021) Department of Sociology; Yörük, Erdem; Hürriyetoğlu, Ali; Duruşan, Fırat; Yoltar, Çağrı; Faculty Member; Teaching Faculty; Researcher; Department of Sociology; College of Social Sciences and Humanities; 28982; N/A; N/A; N/A
    What is the most optimal way of creating a gold standard corpus for training a machine learning system that is designed for automatically collecting protest information in a cross-country context? We show that creating a gold standard corpus for training and testing machine learning models on the basis of randomly chosen news articles from news archives yields better performance than selecting news articles on the basis of keyword filtering, which is the most prevalent method currently used in automated event coding. We advance this new bottom-up approach to ensure generalizability and reliability in cross-country comparative protest event collection from international and local news in different countries, languages, sources and time periods, which entails a large variety of event types, actors, and targets. We present the results of comparing our random-sample approach with keyword filtering. We show that the machine learning algorithms, and particularly state-of-the-art deep learning tools, perform much better when they are trained with the gold standard corpus from a randomly selected set of news articles from China, India, and South Africa. Finally, we also present our approach to overcome the major ethical issues that are intrinsic to protest event coding.
  • Thumbnail Image
    PublicationOpen Access
    The lineage theory of the regional variation of individualism/collectivism in China
    (Frontiers, 2021) Gong, Weigang; Zhu, Meng; Xie, Tian; Department of Sociology; Gürel, Burak; Faculty Member; Department of Sociology; College of Social Sciences and Humanities; 219277
    China has undergone a rapid process of modernization since 1949. The modernization process has accelerated with the development of the market economy and rural-to-urban migration after the 1980s. Nevertheless, Chinese regions still exhibit substantial differences in terms of individualist/collectivist cultural orientations. The rice theory and the climato-economic theory have attempted to explain this variation by analyzing provincial-level data. Based on a quantitative analysis of more granular, county-level variables spanning from the early 1990s until 2010, we offer an alternative account of this cultural variety based on lineage development in different Chinese regions. Using the ArcGIS geographic information system, we first present the regional distribution of individualism/collectivism indicators at the county level through descriptive statistics and spatial analysis. We also run a regression model to analyze county-level data on individualism/collectivism that includes three periods (1990, 2000, and 2010). Our multi-level analysis shows that lineage development is a critical variable that explains more regional variation of culture in China when compared to other variables. While rice farming, the key variable of the rice theory, is a significant variable, its explanatory power is less than the lineage variable. Finally, our analysis shows that the climato-economic theory fails to explain the regional variation of culture.