User Stories record what must be built in projects that use agile practices. User Stories serve both to estimate effort, generally measured in Story Points, and to plan what should be done in a Sprint. Therefore, it is essential to train software engineers on how to create simple, easily readable, and comprehensive User Stories. For that reason, we designed, implemented, applied, and evaluated a web application called User Story Tutor (UST). UST checks the description of a given User Story for readability, and if needed, recommends appropriate practices for improvement. UST also estimates a User Story effort in Story Points using Machine Learning techniques. As such UST may support the continuing education of agile development teams when writing and reviewing User Stories. UST's ease of use was evaluated by 40 agile practitioners according to the Technology Acceptance Model (TAM) and AttrakDiff. The TAM evaluation averages were good in almost all considered variables. Application of the AttrakDiff evaluation framework produced similar good results. Apparently, UST can be used with good reliability. Applying UST to assist in the construction of User Stories is a viable technique that, at the very least, can be used by agile developments to complement and enhance current User Story creation.

In the initial stage of human life, communication, seen as a process of social interaction, was always the best way to reach consensus between the parties. Understanding and credibility in this process are essential for the mutual agreement to be validated. But, how to do it so that this communication reaches the great mass? This is the main challenge when what is sought is the dissemination of information and its approval. In this context, this study presents the ALT software, developed from original readability metrics adapted to the Portuguese language, available on the web, to reduce communication difficulties. The development of the software was motivated by the theory of communicative action of Habermas, which uses a multidisciplinary style to measure the credibility of the discourse in the communication channels used to build and maintain a safe and healthy relationship with the public.

Predicting the potential success of a book in advance is vital in many applications. This could help both publishers and readers in their decision making process whether or not a book is worth publishing and reading, respectively. This prediction could also help authors decide whether a book draft is good enough to send to a publisher. We propose a model that leverages Convolutional Neural Networks along with readability indices. Unlike previous methods, our method includes no count-based, lexical, or syntactic hand-crafted features. Instead, we make use of a pre-trained sentence encoder to encode the book sentences. We highlight the connection between this task and book genre identification by showing that embeddings that are good at capturing the separability of book genres are better for the book success prediction task. We also show that only the first 1K sentences are good enough to predict the successability of books. Our proposed model outperforms strong baselines on this task by as large as 6.4% F1-score.