Nati Ben-Gigi, Binyamin Katzoff, Jonathan Schler, Maayan Zhitomirsky-Geffet
This proposal presents a new conceptual framework for the study of influences and trends in the Responsa literature through the prism of citation networks that are embedded in it, as well as a computational methodology based on advanced machine learning algorithms for automatic citation extraction from Responsa texts. The study investigates to which extent different communities in the Responsa literature used sources of and were influenced by other communities, such as the referring to the sages of Spain in the literature of the sages of France and vice versa, the distribution of Rashi`s commentary on the Talmud, the limited use of the early sources in the literature of Provence sages compared to their acceptance in later periods. The main computational challenge in this task is the variety of formats of references in the citations, as they appear in the texts, that are incomplete and include numerous abbreviations. Sometimes, a reference only includes the name of the author, sometimes only the name of the book, and sometimes only a piece of text from the book appears in the citation. The computational model for automatic citation extraction comprises five layers, each handling a different subtask of the problem. We will present initial results of the ongoing 3-year study funded by Israel Ministry of Science that show the citation analysis of thousands of Responsa files from the Rishonim (“the first ones”) period dated between 11 and 15 centuries. For example, we found that the influence of both Talmuds on the Medieval Responsa literature decreases over time. This and other results of the study provide preliminary reflections of the diverse approaches and influences of the different groups of authors (schools), as determined by temporal and geographic factors. Although the study examined the proposed methodology in the Responsa corpus, it can be applied to the entire Jewish Bookshelf.