Construction and analysis of social networks for historical figures has lately become a popular approach in History and Prosopography.This approach is especially beneficial for providing a global view and automatic mathematical and statistical analysis for large historical corpora, for which researchers are unable to gain much knowledge by even an exhaustive manual exploration.
Jewish Biblical and Rabbinic literature is a great source of ancient wisdom and cultural heritage. It includes a large amount of people such as prophets, political and religious leaders, sages and other historical figures. Amazingly, although these people were spread over the world and through different time periods, they were united and connected by the same text – the Bible. Therefore, the aim of this research is to propose and implement a methodology for construction of a cross-generation social network for Jewish sages to explore their inter-relationships on a large scale, using modern computerized tools for text analysis and graph mining.
At the first stage we define the corpus of the study and a reliable digital resource for this corpus. We work with the text of Mishna (2nd century CE) and Talmud (4th-5th century CE). Next, the following information is retrieved from existing traditional research sources, such as encyclopedia of Jewish sages (as most of these sources have not been digitized, the person-related data is extracted manually and stored in the digital form):
1) A list of sages for the selected corpora. One of the biggest challenges with sages’ names is their ambiguity and a large number of namesakes. To tackle this problem we add identifying discriminative features to each name (e.g. father’s name or place of birth).
2) A list of basic relationships between sages, e.g. family relationships, teacher-student, time period, place, possessing a similar political/social/professional role, studying in the same institution, participation in the same event.
Finally, the above basic relationship list can be further extended with text-based relationships, such as sages who cite each other, disagree, or comment on the same section of the biblical text. This is achieved by automatically learning lexical patterns in which pairs of sages co-occur in texts and using them to extract the corresponding relations. The historical data in the built networkbecomes accessible to researchers from the humanities and will take their research capabilities to the next level.
Zhitomirsky-Geffet M. and Prebor G. “Towards a cross-generation social network for Jewish sages”. Poster in the Proceedings of the Digital Humanities 2016 conference (DH2015), Krakov, Poline, July, 2016.