--- title: Can you collect daily PMS symptom information from women using conversation instead of long forms? description: Yes. Asking women about symptom clusters (groups of related symptoms) instead of individual symptoms works almost as well, captures moderate-to-high symptoms url: https://niyora.com/research/papers/scale-to-dialogue-low-burden-elicitation-of-daily-premenstrual-symptom-ratings-2026/ --- - [Niyora](https://niyora.com/) - [Research](https://niyora.com/research/) - [Library](https://niyora.com/research/library/) - Can you collect daily PMS symptom information from women using conversation instead of long forms? Study, 2026 # Can you collect daily PMS symptom information from women using conversation instead of long forms? Yes. Asking women about symptom clusters (groups of related symptoms) instead of individual symptoms works almost as well, captures moderate-to-high symptoms reliably, and cuts the number of questions by half. Early or limited evidence 36 women (used to test and develop a language model tool) ## What they did Researchers used a language model to conduct conversations with women about their daily PMS symptoms. They tested whether asking about symptom clusters (like mood and stress together) worked as well as asking each symptom individually. They gathered data from 36 women over 360 participant-days. ## What they found Asking 3 cluster questions captured 80.94% of moderate-or-higher symptoms. It achieved 97.45% agreement within one symptom-severity level. The three-cluster approach cut the number of questions in half compared to asking all symptoms separately. ## What it means for you Research teams can collect daily symptom data more efficiently by asking about related symptoms together instead of one-by-one. This makes it easier for women to track symptoms for research purposes. However, this is about tools for research, not treatments for PMDD. 36 women 360 participant-days of symptom data 80.94% capture rate for moderate-or-higher symptoms ## About the study Original title Scale-to-Dialogue: Low-Burden Elicitation of Daily Premenstrual Symptom Ratings with Small Language Models Authors Yifan Wang Journal arXiv (Cornell University) Year 2026 Study design Study What was tested Three-cluster question strategy versus six-item strategy Open access Yes Read the paper [doi.org/10.48550/arxiv.2608.08746](https://doi.org/10.48550/arxiv.2608.08746) Original abstract Prospective daily symptom tracking is central to premenstrual health assessment, but repeated ordinal forms impose substantial response burden. We formulate conversational administration as an ordinal label-recovery problem: the system actively elicits a small set of symptom clusters and maps each response to the original severity labels. We used 3,320 complete participant-days from the mcPHASES dataset, covering cramps, mood swing, fatigue, sleep issues, stress, and bloating on a six-level scale. Six participants were reserved for development and 36 for a frozen evaluation comprising 360 participant-days and 2,160 item labels. A ModernBERT evidence gate detected whether a symptom was expressed, and Qwen2.5-1.5B-Instruct produced deterministic structured severity scores. Fixed six-item questioning achieved a quadratic weighted kappa of 0.976, whereas three joint symptom-cluster questions achieved 0.913, 97.45% agreement within one severity level, and 80.94% recall for moderate-or-higher symptoms while reducing questions by 50%. Open-first adaptive policies required 3.92-5.98 questions and produced lower agreement than the corresponding fixed policies. Participant-cluster bootstrap analysis estimated a kappa difference of -0.062 (95% CI -0.076 to -0.048) between the three-cluster and six-item strategies. Active cluster-level elicitation provides a direct, local-model route from natural conversation to reusable daily symptom labels. Reproduced under CC-BY. ## Topics [Premenstrual syndrome (PMS)](https://niyora.com/research/topics/condition-pms/)[Quality of life and daily functioning](https://niyora.com/research/topics/life-area-quality-of-life/) Research tells you what helps on average. Niyora helps on the day it hits. Calm down, see it another way, and decide what to say, with a PMS and PMDD app built by a doctor. ## Related studies Cohort study, 2026 Is PMS becoming more common and more disabling worldwide? Randomised trial, 2026 Does yoga or Pilates help reduce PMS symptoms? Randomised trial, 2026 Does Kundalini Reiki help reduce PMS symptoms and improve quality of life? Randomised trial, 2026 Does taking alpha-lactalbumin supplement for three months help with period-related symptoms? Systematic review, 2026 Do mindfulness and relaxation techniques help with PMS symptoms? Randomised trial, 2026 Does a warm footbath help PMS symptoms and sleep quality? Ask AI about this page Copy prompt ChatGPT ↗ Claude ↗ Perplexity ↗ Google AI Mode ↗ Grok ↗