Abstract
Corpus-based writing assistants are aimed to show how words are used in real context: they provide word use examples from which users can (1) draw inspiration for their writing and (2) understand how words are used together to improve their own writing. Although the idea of integrating a corpus-based writing assistant (concordancer) into word processors is not new, their integration is designed to be not as straightforward as writing in a word processor. In this paper, we present WriteBetter, a corpus-based writing assistant designed to be integrated into Microsoft Word, Google Docs, and Overleaf. This integration makes its use straightforward and easy as users can see corpus-based examples (1) in real-time while writing in the word processor or (2) just selecting a piece of text in their document. This facilitates user-corpus interaction as the required user's interaction is minimal. After contextualising the state of the art regarding the benefits of corpus-consultation, we discuss the design features of WriteBetter that make it novel in relation to other tools. Next, we present a user evaluation of the first version of WriteBetter, which was carried out on 11 undergraduate students of a Chilean university, who were asked to trial the software while writing in English. Based on this evaluation, we designed a new version of WriteBetter, which was further evaluated online on 36 users. WriteBetter is now available for everyone as SaaS.
Highlights
Academic writing is a challenge for many people
We present WriteBetter, a corpus-based writing assistant designed to be seamlessly integrated into the word processor (Microsoft Word, Google Docs, and Overleaf until now)
We aim to identify any learner-corpus interaction mediated by WriteBetter and evaluate how, and to what extent, such an interaction changed their writing
Summary
That is why the market is full of writing assistants aimed at providing feedback to improve writing. A minor class of writing assistants (e.g., WriteFull, Ludwig), in contrast, provide corpus-based examples according to the word searched. Based on these examples, users can (1) draw inspiration for their writing and (2) understand how words are used together to improve their own writing. Corpus-based tools are built on the concept of concordance: searching a word/chunk of text, sentences containing that word/chunk of text are displayed surrounded by their co-text. In contrast to the most traditional writing assistants, a corpus-based writing assistant requires users to make an additional effort since different examples must be explored to select the most relevant ones that fit what users are writing.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
