New tool could help authors bust writer's block in novel-length works

Authors experiencing writer's block could soon have a new way to help develop the next section of their story. Researchers at the Penn State College of Information Sciences and Technology recently introduced a new technology that forecasts the future development of an ongoing written story. In their approach, researchers first characterize the narrative world using over 1,000 different "semantic frames," where each frame represents a cluster of concepts and related knowledge. A predictive algorithm then looks at the preceding story and predicts the semantic frames that might occur in the next 10, 100, or even 1,000 sentences in an ongoing story. Unlike current automated text generated methods, the researchers' approach could help authors to craft language for the follow-up story arc beyond the scope of a few sentences, a limitation of existing models.