Umit Boz

Modeling Sociocultural phenomena in discourse

In this paper, we describe a novel approach to computational modeling and understanding of social and cultural phenomena in multi-party dialogues. We developed a two-tier approach in which we first detect and classify certain sociolinguistic behaviors, including topic control, disagreement, and involvement, that serve as first-order models from which presence the higher level social roles, such as leadership, may be inferred.

Using imageability and topic chaining to locate metaphors in linguistic corpora

The reliable automated identification of metaphors still remains a challenge in metaphor research due to ambiguity between semantic and contextual interpretation of individual lexical items. In this article, we describe a novel approach to metaphor identification which is based on three intersecting methods: imageability, topic chaining, and semantic clustering. Our hypothesis is that metaphors are likely to use highly imageable words that do not generally have a topical or semantic association with the surrounding context. Our method is thus the following: (1) identify the highly imageable portions of a paragraph, using psycholinguistic measures of imageability, (2) exclude imageability peaks that are part of a topic chain, and (3) exclude imageability peaks that show a semantic relationship to the main topics. We are currently working towards fully automating this method for a number of languages.

Student leadership in small group science inquiry

Background: Science educators have sought to structure collaborative inquiry learning through the assignment of static group roles. This structural approach to student grouping oversimplifies the complexities of peer collaboration and overlooks the highly dynamic nature of group activity. Purpose: This study addresses this issue of oversimplification of group dynamics by examining the social leadership structures that emerge in small student groups during science inquiry. Sample: Two small student groups investigating the burning of a candle under a jar participated in this study. Design and method: We used a mixed-method research approach that combined computational discourse analysis (computational quantification of social aspects of small group discussions) with microethnography (qualitative, in-depth examination of group discussions). Results: While in one group social leadership was decentralized (i.e., students shared control over topics and tasks), the second group was dominated by a male student (centralized social leadership). Further, decentralized social leadership was found to be paralleled by higher levels of student cognitive engagement. Conclusions: It is argued that computational discourse analysis can provide science educators with a powerful means of developing pedagogical models of collaborative science learning that take into account the emergent nature of group structures and highly fluid nature of student collaboration.

Chinese and American Leadership Characteristics: Discovery and Comparison in Multi-party On-Line Dialogues

Recent advances in automated analysis of on-line chat data allow us to draw conclusions about social behavior, such as leadership, in small groups previously possible only through manual methods of observation and analysis. We have applied such methods to comparable English and Chinese language data, defined a new language use called Tension Focus, and demonstrate its different effects in the data in these two languages.