LLM-MC-Affect: LLM-Based Monte Carlo Modeling of Affective Trajectories and Latent Ambiguity for Interpersonal Dynamic Insight
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913145666142208 |
|---|---|
| author | Lin, Yu-Zheng Shih, Bono Po-Jen Encinas, John Paul Martin Achom, Elizabeth Victoria Abraham Patel, Karan Himanshu Pacheco, Jesus Horacio Shao, Sicong Dass, Jyotikrishna Salehi, Soheil Satam, Pratik |
| author_facet | Lin, Yu-Zheng Shih, Bono Po-Jen Encinas, John Paul Martin Achom, Elizabeth Victoria Abraham Patel, Karan Himanshu Pacheco, Jesus Horacio Shao, Sicong Dass, Jyotikrishna Salehi, Soheil Satam, Pratik |
| contents | Emotional coordination is a core property of human interaction that shapes how relational meaning is constructed in real time. While text-based affect inference has become increasingly feasible, prior approaches often treat sentiment as a deterministic point estimate for individual speakers, failing to capture the inherent subjectivity, latent ambiguity, and sequential coupling found in mutual exchanges. We introduce LLM-MC-Affect, a probabilistic framework that characterizes emotion not as a static label, but as a continuous latent probability distribution defined over an affective space. By leveraging stochastic LLM decoding and Monte Carlo estimation, the methodology approximates these distributions to derive high-fidelity sentiment trajectories that explicitly quantify both central affective tendencies and perceptual ambiguity. These trajectories enable a structured analysis of interpersonal coupling through sequential cross-correlation and slope-based indicators, identifying leading or lagging influences between interlocutors. To validate the interpretive capacity of this approach, we utilize teacher-student instructional dialogues as a representative case study, where our quantitative indicators successfully distill high-level interaction insights such as effective scaffolding. This work establishes a scalable and deployable pathway for understanding interpersonal dynamics, offering a generalizable solution that extends beyond education to broader social and behavioral research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03645 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LLM-MC-Affect: LLM-Based Monte Carlo Modeling of Affective Trajectories and Latent Ambiguity for Interpersonal Dynamic Insight Lin, Yu-Zheng Shih, Bono Po-Jen Encinas, John Paul Martin Achom, Elizabeth Victoria Abraham Patel, Karan Himanshu Pacheco, Jesus Horacio Shao, Sicong Dass, Jyotikrishna Salehi, Soheil Satam, Pratik Computation and Language Computers and Society Emotional coordination is a core property of human interaction that shapes how relational meaning is constructed in real time. While text-based affect inference has become increasingly feasible, prior approaches often treat sentiment as a deterministic point estimate for individual speakers, failing to capture the inherent subjectivity, latent ambiguity, and sequential coupling found in mutual exchanges. We introduce LLM-MC-Affect, a probabilistic framework that characterizes emotion not as a static label, but as a continuous latent probability distribution defined over an affective space. By leveraging stochastic LLM decoding and Monte Carlo estimation, the methodology approximates these distributions to derive high-fidelity sentiment trajectories that explicitly quantify both central affective tendencies and perceptual ambiguity. These trajectories enable a structured analysis of interpersonal coupling through sequential cross-correlation and slope-based indicators, identifying leading or lagging influences between interlocutors. To validate the interpretive capacity of this approach, we utilize teacher-student instructional dialogues as a representative case study, where our quantitative indicators successfully distill high-level interaction insights such as effective scaffolding. This work establishes a scalable and deployable pathway for understanding interpersonal dynamics, offering a generalizable solution that extends beyond education to broader social and behavioral research. |
| title | LLM-MC-Affect: LLM-Based Monte Carlo Modeling of Affective Trajectories and Latent Ambiguity for Interpersonal Dynamic Insight |
| topic | Computation and Language Computers and Society |
| url | https://arxiv.org/abs/2601.03645 |