Modeling and Visualization

With the ease of posting and receiving information in the enterprise, the flood of information may be difficult for users to efficiently digest. The posts themselves are often sequential, where the sequence may simply be in time, as in Slack posts, web-pages in users’ browsing histories, and news articles. In addition to time, the items may be ordered based on content and other meta-data. Visual analytic techniques can help users gain new insights in an information space and identify implicit relations among items. By visualizing succinct representations, such as abstractive summaries, of the content which are extracted through modeling and analysis, users will more easily grasp the range of information as well as identify information that is important to them. Recommendation can be used to filter and rank items for use in visualization, as well as to independently alert a user with important information. Some posts may be written in a style that is difficult to understand, due to technical terminology or poor grammar. To help users more easily digest such information, text style transfer could transform posts and articles into simpler texts with better grammar or style, e.g., more polite.