Beyond Likert Scales: Convergent Validity of an NLP-Based Future Self-Continuity Assessment from Verbal Data

Psychological assessment using self-report Likert items suffers from numerous inherent biases. These biases limit our capability to assess complex psychological constructs such as Future Self-Continuity (FSC), i.e. the perceived connection between one's present and future self. However, recent advances in Natural Language Processing (NLP) and Large Language Models (LLMs) have opened new possibilities for psychological assessment. In this paper, we introduce a novel method of psychological assessment applied to measuring FSC that uses an LLM for NLP of transcripts from self-recorded audio of responses to 15 structured interview prompts developed from FSC theory and research. 164 whitelisted MTurk workers completed an online survey and interview task. Claude 3.5 Sonnet was used to process the transcripts and generate quantitative scores. The resulting FSC scores (including total score, and the similarity, vividness, and positivity components) showed significant correlations with scores on the Future Self-Continuity Questionnaire (FSCQ), a well-validated Likert item measure of FSC, supporting the new method's convergent validity. A Bland-Altman analysis indicating general agreement with standard FSCQ scores, replication using an updated Claude 3.5 Sonnet model, and the strong correlations between NLP-based FSC scores using the two models supports the new assessment method's validity and robustness. This measurement approach can inform treatment planning and interventions by providing clinicians with a more authentic FSC assessment. Beyond FSC, this NLP/LLM approach can enhance psychological assessment broadly, with significant implications for research and clinical practice.