A5031400973- Speech and dialogue systems
- Natural Language Processing Techniques
- Topic Modeling
- Intelligent Tutoring Systems and Adaptive Learning
- Multi-Agent Systems and Negotiation
- Innovative Teaching and Learning Methods
- Semantic Web and Ontologies
- Online Learning and Analytics
- Language, Metaphor, and Cognition
- Online and Blended Learning
- Video Analysis and Summarization
- AI-based Problem Solving and Planning
- Advanced Text Analysis Techniques
- Emotion and Mood Recognition
- Language, Discourse, Communication Strategies
- Sentiment Analysis and Opinion Mining
- Text Readability and Simplification
- AI in Service Interactions
- Social Robot Interaction and HRI
- Multimedia Communication and Technology
- Data Visualization and Analytics
- Discourse Analysis in Language Studies
- Cognitive Science and Mapping
- Speech Recognition and Synthesis
- Music and Audio Processing
University of Edinburgh
2015-2024
University of Pittsburgh
1991-2019
East Stroudsburg University
2018
University of Notre Dame
2018
Tata Consultancy Services (India)
2018
Columbus Center
2010
University of California, Los Angeles
1983-1998
Carnegie Mellon University
1995
University of Southern California
1985
Marina Del Rey Hospital
1984
In this paper, we investigate the utility of linguistic features for detecting sentiment Twitter messages. We evaluate usefulness existing lexical resources as well that capture information about informal and creative language used in microblogging. take a supervied approach to problem, but leverage hashtags data building training data.
Abstract The psycholinguistic literature has identified two syntactic adaptation effects in language production: rapidly decaying short‐term priming and long‐lasting adaptation. To explain both effects, we present an ACT‐R model of based on a wide‐coverage, lexicalized theory that explains as facilitation lexical access. In this model, well‐established mechanisms, base‐level learning spreading activation, account for long‐term priming, respectively. Our simulates incremental production...
Self-Regulated Learning (SRL) is related to increased learning performance. Scaffolding learners in their SRL activities a computer-based environment can help improve outcomes, because students do not always regulate spontaneously. Based on theoretical assumptions, scaffolds should be continuously adaptive and personalized students' ongoing progress order promote SRL. The present study aimed investigate the effects of analytics-based scaffolds, facilitated by rule-based artificial...
The explainable expert systems framework (EES), in which the focus is on capturing those design aspects that are important for producing good explanations, including justifications of system's actions, explications general problem-solving strategies, and descriptions terminology, discussed. EES was developed as part Strategic Computing Initiative US Dept. Defense's Defense Advanced Research Projects Agency (DARPA). both principles from system derived how can be represented EES. Program...
Explanation is an interactive process requiring a dialogue between advice-giver and advice-seeker. In this paper, we argue that in order to participate with its users, generation system must be capable of reasoning about own utterances therefore maintain rich representation the responses it produces. We present text planner constructs detailed plan, containing intentional, attentional, rhetorical structures generates.
Principled development techniques could greatly enhance the understandability of expert systems for both users and system developers. Current have limited explanatory capabilities present maintenance problems because a failure to explicitly represent knowledge reasoning that went into their design. This paper describes paradigm constructing which attempts identify tacit knowledge, provide means capturing it in bases systems, and, apply towards more perspicuous machine-generated explanations...
Abstract Contemporary research that looks at self-regulated learning (SRL) as processes of events derived from trace data has attracted increasing interest over the past decade. However, limited been conducted into validity trace-based measurement protocols. In order to fill this gap in literature, we propose a novel validation approach combines theory-driven and data-driven perspectives increase interpretations SRL extracted trace-data. The main contribution consists three alignments...
Abstract In recent years, unobtrusive measures of self-regulated learning (SRL) processes based on log data recorded by digital environments have attracted increasing attention. However, researchers also recognised that simple navigational or time spent pages are often not fine-grained enough to study complex SRL processes. Recent advances in data-capturing technologies enabled go beyond logs measure with multi-channel data. What can reveal about processes, and what extent the addition...
Abstract Background Many learners struggle to productively self‐regulate their learning. To support the learners' self‐regulated learning (SRL) and boost achievement, it is essential understand cognitive metacognitive processes that underlie SRL. measure these processes, contemporary SRL researchers have largely utilized think aloud or trace data, however, not without challenges. Objectives In this paper, we present findings of a study investigated how concurrent analysis integration data...