Ran Liu

Carnegie Mellon University | CMU · Human-Computer Interaction Institute

Leveraging a scientific infrastructure for exploring how students learn, we have developed cognitive and statistical models of skill acquisition and used them to understand fundamental similarities and differences across learners. Our primary question was why do some students learn faster than others? Or, do they? We model data from student perform...

Leveraging a scientific infrastructure for exploring how students learn, we have developed cognitive and statistical models of skill acquisition and used them to understand fundamental similarities and differences across learners. Our primary question was why do some students learn faster than others? Or do they? We model data from student performa...

Using data to understand learning and improve education has great promise. However, the promise will not be achieved simply by AI and Machine Learning researchers developing innovative models that more accurately predict labeled data. As AI advances, modeling techniques and the models they produce are getting increasingly complex, often involving t...

Student mistakes are often not random but, rather, reflect thoughtful yet incorrect strategies. In order for educational technologies to make full use of students' performance data to estimate the knowledge of a student, it is important to model not only the conceptions but also the misconceptions that a student's particular pattern of successes an...

Speech perception depends on long-term representations that reflect regularities of the native language. However, listeners rapidly adapt when speech acoustics deviate from these regularities due to talker idiosyncrasies such as foreign accents and dialects. To better understand these dual aspects of speech perception, we probe native English liste...

A growing body of research suggests that accounting for student-specific variability in educational data can improve modeling accuracy and may have implications for individualizing instruction. The Additive Factors Model (AFM), a logistic regression model used to fit educational data and discover/refine skill models of learning, contains a paramete...

Additive Factors Model (AFM) and Performance Factors Analysis (PFA) are two popular models of student learning that employ logistic regression to estimate parameters and predict performance. This is in contrast to Bayesian Knowledge Tracing (BKT) which uses a Hidden Markov Model formalism. While all three models tend to make similar predictions, th...

Adults learn many new tasks with ease, but acquiring the sounds of a new language is notoriously difficult. Decades of attempts to develop effective training regimens have focused primarily on highly explicit approaches to training adults to categorize non-native speech sounds. Participants are aware of the phonetic distinctions they are learning,...

Automated techniques have proven useful for improving models of student learning even beyond the best human-generated models. There has been concern among the EDM community about whether small prediction improvements matter. We argue that they can be quite significant when they are interpretable and actionable, but the importance of generating mean...

Cognitive neuroscientists studying sound and speech learning have successfully used videogames as a research vehicle. Neuroscientists and game developers worked together to produce a game built to entice participants to longer periods of play, while enabling researchers to easily configure presentation parameters in support of future studies. A spa...

Voices have unique acoustic signatures, contributing to the acoustic variability listeners must contend with in perceiving speech, and it has long been proposed that listeners normalize speech perception to information extracted from a talker's speech. Initial attempts to explain talker normalization relied on extraction of articulatory referents,...

The ability to flexibly adapt long?term speech category representations to informative regularities in short?term input is critical for on?line speech perception. The present experiment investigates how short?term changes in the variability of two distinct acoustic cues affect the relative weighting of the cues for speech categorization. Native Eng...

Native language experience plays a critical role in shaping speech categorization, but the exact mechanisms by which it does so are not well understood. Investigating category learning of nonspeech sounds with which listeners have no prior experience allows their experience to be systematically controlled in a way that is impossible to achieve by s...

Most studies of L2 speech perception seek to characterize-at least implicitly-how the similarity among L2 speech sound categories is shaped by L1 experience. Intercategory similarity for native language speakers is rarely considered, however. Here, we derive two indices of graded intercategory similarity for a front vowel series (pin, pen, and pan)...