There has been growing interest in utilizing natural language processing (NLP) algorithms in Aviation Safety [1]. This interest has extended to leveraging the decades of records publicly available on the Aviation Safety Reporting System (ASRS)∗ [2–5]. While related literature has given more emphasis in lessons learned from the narratives, our prior work [2] has focused on using NLP to support narrative search in the ASRS. Specifically, we evaluated if the use of alternative search mechanisms to keyword search, such as the retrieval of related narratives even without matching keywords (e.g. [6]), could improve narrative discovery.
A difficulty in experimenting alternative search mechanisms in any information retrieval task is the lack of ground truth. Namely, given a database of narratives D, a user specified query {q ∈ Q}, and a keyword k or machine learning m1 search retrieval mechanism ({k, m1 ∈ M}), we are unable to empirically determine retrieval performance between Rk,q = k (q, D), the set of reports retrieved by keyword search, or Rm1,q = m1 (q, D), the set of reports retrieved by a machine learning algorithm.
To address this limitation, we propose Kaona, a lightweight interface which enables the prototyping of alternative search retrieval tasks, by tracking user experience both explicitly (user-specified feedback), or implicitly (user navigation through interface affordances). Differently from distracting requests for feedback during user navigation, Kaona collects explicit feedback from users by mapping them to affordances which support the user workflow, while obtaining ground truth information for learning tasks.