CyWrite: Intelligent support for students, teachers, and researchers of writing

UPDATE: Early Adoption

We are thrilled to be accepting applications from ESL programs that would like to use the CyWrite technology in their classrooms.

How it started

The idea for CyWrite emerged from our research into uses of  the commercial automated writing evaluation (AWE) tool Criterion by Educational Testing Service (ETS) by learners and teachers of English as a second language (ESL). This research confirmed the potential of AWE but also found numerous issues that needed to be addressed, including the accuracy, clarity, and explicitness of formative feedback; learners’ and teachers’ confidence in AWE scoring; questions of when and how learners should use AWE while learning to write academically; and the usability and functionality of the system itself. We started to investigate alternate approaches that could inform the design of improved AWE systems, but to operationalize our ideas we needed a system that was customizable. In contrast to existing systems originally designed for standardized testing, CyWrite has been developed to support not only testing but also the writing instruction and research.

How it works

The AWE component of CyWrite relies on a hybrid (statistical and rule-based) natural language processing (NLP) engine for the detection of various word-, sentence-, paragraph-, and text-level features, for example, spelling and grammatical errors, stylistic issues, and certain discourse patterns. Formative feedback to the learner is generated based on the detected features and delivered either concurrently with the composition process (for example, in the form of the “red squiggly line” for the spelling errors, or “comments on the margin” for poor stylistic choices), or episodically, that is, after the learner submits his or her draft for automated evaluation.

How we’re extending CyWrite’s reach

CyWrite was engineered as a modular system. Open real-time application programming interfaces (APIs) allow for extending the functionality of CyWrite via third-party extension modules (or plug-ins), and also for incorporating the core CyWrite technology into other applications. Such extensibility of the system has logically led to broadening its scope from just an AWE tool to a platform for building complex learning environments. For example, at Iowa State University, a writing support environment based on the CyWrite AWE technology is implemented in academic writing classes for non-native speakers of English, with custom curriculum-specific workflow modules being integrated with the core via the APIs. Additional functionality, such as integration of teacher-provided and peer feedback with the formative feedback automatically generated, is continually being developed and tried out in instructional settings.

How to stay updated on the project

We would love to stay in touch with you. If you would like to be posted on the CyWrite project news, consider subscribing to our monthly updates. The subscription is powered by Iowa State University mail-list system, so it is easy to unsubscribe at any time.