← Research

Artificial Intelligence in the automatic coding of interviews on Landscape Quality Objectives. Comparison and case study

Mario Burgui-Burgui

In this study, we conducted a comparative analysis of the automated coding provided by three Artificial Intelligence functionalities (At-las.ti, ChatGPT and Google Bard) in relation to the manual coding of 12 research interviews focused on Landscape Quality Objectives for a small island in the north of Cuba (Cayo Santa Mar\'ia). For this purpose, the following comparison criteria were established: Accuracy, Comprehensiveness, Thematic Coherence, Redundancy, Clarity, Detail and Regularity. The analysis showed the usefulness of AI for the intended purpose, albeit with numerous flaws and shortcomings. In summary, today the automatic coding of AIs can be considered useful as a guide towards a subsequent in-depth and meticulous analysis of the information by the researcher. However, as this is such a recently developed field, rapid evolution is expected to bring the necessary improvements to these tools.

PDF ↗

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace