Latent Semantic Analysis (LSA) plays an important role in analyzing text data from education settings. LSA represents meaning of words and sets of words by vectors from a k-dimensional space generated from a selected corpus. While the impact of the value of k has been investigated by many researchers, the impact of the selection of documents and…

Background: Pedagogical agents are computerized talking heads or embodied animated avatars that help students learn by performing actions and holding conversations with the students in natural language. Dialogues occur between a tutor agent and the student in the case of AutoTutor and other intelligent tutoring systems with natural language…

There is an emerging trend in higher education for the adoption of massive open online courses (MOOCs). However, despite this interest in learning at scale, there has been limited work investigating the impact MOOCs can play on student learning. In this study, we adopt a novel approach, using language and discourse as a tool to explore its…

This study investigates a possible way to analyze chat data from collaborative learning environments using epistemic network analysis and topic modeling. A 300-topic general topic model built from TASA (Touchstone Applied Science Associates) corpus was used in this study. 300 topic scores for each of the 15,670 utterances in our chat data were…

Formality has long been of interest in the study of discourse, with periodic discussions of the best measure of formality and the relationship between formality and text categories. In this research, we explored what features predict formality as humans perceive the construct. We categorized a corpus consisting of 1,158 discourse samples published…

Coh-Metrix analyzes texts on multiple measures of language and discourse that are aligned with multilevel theoretical frameworks of comprehension. Dozens of measures funnel into five major factors that systematically vary as a function of types of texts (e.g., narrative vs. informational) and grade level: narrativity, syntactic simplicity, word…

Coh-Metrix analyzes texts on multiple measures of language and discourse that are aligned with multilevel theoretical frameworks of comprehension. Dozens of measures funnel into five major factors that systematically vary as a function of types of texts (e.g., narrative vs. informational) and grade level: narrativity, syntactic simplicity, word…

Recent studies have used Coh-Metrix, an automated text analyzer, to assess differences in language characteristics across different genres and academic disciplines (Graesser, McNamara, & Kulikowich, 2011; McNamara, Graesser, McCarthy, & Cai, 2014). Coh-Metrix analyzes text on many constructs at different levels, including Word Concreteness…

An emerging trend toward computer-mediated collaborative learning environments promotes lively exchanges between learners in order to facilitate learning. Discourse can play an important role in enhancing epistemology, pedagogy, and assessments in these environments. In this paper, we highlight some of our recent work showing the advantages using…

This study addresses the need in discourse psychology for computational techniques that analyze text on multiple levels of cohesion and text difficulty. Discourse psychologists often investigate phenomena related to discourse processing using lengthy texts containing multiple paragraphs, as opposed to single word and sentence stimuli.…

Presents a taxonomy of jokes and wit as a useful, descriptive tool. Argues that humor processing may occur in a parallel rather than serial fashion by contrasting a serial-processing, incongruity-resolution model with an alternative dual-processing model. Also presents a taxonomy of the social functions of wit. (JK)

Defines quantitative-discourse psychology. Illustrates its practice in five research projects, all of which examined naturalistic discourse, investigating: reading time; inference generation; construction of multiple agents (narrators, characters) in literary short stories; tutorial dialog; and dialog patterns in two-party conversations. Notes a…

Describes the seven main components of QUEST, a cognitive model of question answering that attempts to simulate the answers adults produce when they answer different types of questions, both closed class and open class. Illustrates how the model could be applied to different types of knowledge structures, including causal networks, goal…

Tests the QUEST model of question answering in naturalistic settings and in settings with complex pragmatic constraints: telephone surveys, business interactions, filmed interviews, and interviews on popular television programs. Finds that QUEST explains most of the answers in these contexts and virtually all of the answers that refer to the…

Argues that an adequate theory of inference generation should accurately predict whether particular classes of knowledge-based inferences are generated online during text comprehension. Proposes a "constructionist" theory which accounts for the findings of cognitive psychology and discourse processing. (HB)