A Personalized Recommender System for Writing in the Internet Age

Writing is a complex task and several computer systems have been developed in order to support writing. Most of these systems, however, are mainly designed with the purpose of supporting the processes of planning, organizing and connecting ideas. In general, these systems help writers to formulate external visual representations of their ideas and connections of the main topics that should be addressed in the paper, sequence of the sections, etc. With the advent of the world wide web, writing and finding information for the written text has become increasingly intertwined. Consequently, it is necessary to develop systems able to support the task of finding relevant information during writing, without interfering with the writing process proper. In this paper we present the Proactive Recommender System: À propos. This system is being developed in order to support writers in the difficult task of finding appropriate relevant information during writing. We raise the question whether the tendency to interleave (re)search and writing implies a need for developing more comprehensive models of the cognitive processes involved in writing scientific and policy papers.