Spaces:
Sleeping
Sleeping
Create guidelines.md
Browse files- guidelines.md +110 -0
guidelines.md
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
# Annotation of Simulated Patients
|
| 3 |
+
|
| 4 |
+
## Goal of the Task
|
| 5 |
+
|
| 6 |
+
This annotation task aims to support research on **simulated patients** used in the training of psychotherapists. Simulated patients may be portrayed by **human actors or AI-generated agents**, and are designed to engage in realistic psychotherapy sessions with a therapist.
|
| 7 |
+
|
| 8 |
+
Your role as an annotator is to carefully evaluate **how the patient is portrayed within the therapy session**, focusing on:
|
| 9 |
+
|
| 10 |
+
1. The patient’s psychological and emotional presentation during the session
|
| 11 |
+
2. The patient’s conversational style and interactional behavior
|
| 12 |
+
3. Behavioral and pragmatic properties of the patient’s responses
|
| 13 |
+
4. How accurately and consistently the patient adheres to a provided role description
|
| 14 |
+
5. How realistic the patient appears as a therapy client overall
|
| 15 |
+
|
| 16 |
+
Your annotations will help us understand which aspects of patient behavior contribute to realism and role fidelity in simulated psychotherapy settings.
|
| 17 |
+
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
## Important Notes
|
| 21 |
+
|
| 22 |
+
- The dataset contains a **mix of human-acted and AI-generated simulated patients**.
|
| 23 |
+
- **Do not attempt to identify** whether a patient is human or AI.
|
| 24 |
+
- **Do not compare** different sessions or simulated patients against each other.
|
| 25 |
+
- **Do not evaluate** which type of simulated patient is “better.”
|
| 26 |
+
|
| 27 |
+
Please focus exclusively on:
|
| 28 |
+
- The **therapy session transcript**
|
| 29 |
+
- The **role description provided**
|
| 30 |
+
- The **specific questions asked in the annotation interface**
|
| 31 |
+
|
| 32 |
+
Your goal is to provide **accurate, consistent, and equivalent judgments** across all sessions.
|
| 33 |
+
|
| 34 |
+
---
|
| 35 |
+
|
| 36 |
+
## Annotation Task Overview
|
| 37 |
+
|
| 38 |
+
For each annotation case, you will complete **two steps**.
|
| 39 |
+
|
| 40 |
+
### Step 1: Annotation of the Therapy Session
|
| 41 |
+
|
| 42 |
+
In Step 1, you will be shown a **full transcript** of a simulated therapy session between:
|
| 43 |
+
|
| 44 |
+
- **T** = Therapist
|
| 45 |
+
- **P** = Patient
|
| 46 |
+
|
| 47 |
+
Please read the entire session carefully before answering any questions.
|
| 48 |
+
|
| 49 |
+
All questions in this step refer **only to the patient (P)** and their behavior **within the session itself**, independent of any role description. You will answer questions across **three thematic areas**.
|
| 50 |
+
|
| 51 |
+
1. Presentation of the Patient’s Psychological State
|
| 52 |
+
* These questions focus on how the patient presents emotionally and psychologically during the session.
|
| 53 |
+
* Base your answers strictly on what is **expressed or implied in the dialogue**, not on assumptions about diagnoses or intent.
|
| 54 |
+
2. Patient’s Conversational Style
|
| 55 |
+
* These questions address **how the patient communicates** with the therapist.
|
| 56 |
+
* Focus on observable conversational behavior, not on whether responses are “good” or “bad” from a therapeutic perspective.
|
| 57 |
+
3. Behavioral and Pragmatic Properties
|
| 58 |
+
* These questions concern the **interactional and pragmatic behavior** of the patient in the therapeutic context.
|
| 59 |
+
* Rely only on evidence from the transcript.
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Step 2: Annotation of True-to-Patient Properties
|
| 63 |
+
|
| 64 |
+
In Step 2, you will be shown:
|
| 65 |
+
|
| 66 |
+
1. The **role description** that was provided to the simulated patient before the session
|
| 67 |
+
2. The therapy session transcript (dropdown) for reference if needed
|
| 68 |
+
|
| 69 |
+
The role description may include information such as:
|
| 70 |
+
|
| 71 |
+
- Background and life context
|
| 72 |
+
- Psychological or emotional difficulties
|
| 73 |
+
- Expected demeanor or personality traits
|
| 74 |
+
- Interaction style and tendencies in therapy
|
| 75 |
+
- Attitudes toward therapy or the therapist
|
| 76 |
+
|
| 77 |
+
Please read the role description carefully before answering the questions in this step. Your task is to assess the following:
|
| 78 |
+
|
| 79 |
+
1. **Role Fidelity**
|
| 80 |
+
* How well does the patient’s behavior in the session align with the provided role description?
|
| 81 |
+
* Are key characteristics from the description reflected consistently in the interaction?
|
| 82 |
+
* Are there noticeable deviations, contradictions, or omissions?
|
| 83 |
+
2. **Realism as a Therapy Patient**
|
| 84 |
+
* Does the patient come across as a plausible, realistic therapy client?
|
| 85 |
+
* Do the emotional, conversational, and behavioral patterns resemble what one might expect in a real psychotherapy session?
|
| 86 |
+
|
| 87 |
+
When answering these questions, consider the **entire session as a whole**, rather than isolated turns.
|
| 88 |
+
|
| 89 |
+
---
|
| 90 |
+
|
| 91 |
+
## General Annotation Guidelines
|
| 92 |
+
|
| 93 |
+
- Base all judgments **only on the materials provided** (transcript and role description).
|
| 94 |
+
- Avoid over-interpreting or filling in gaps with assumptions.
|
| 95 |
+
- If information is unclear or insufficiently evidenced, select the most appropriate response option.
|
| 96 |
+
- Apply rating scales **consistently** across different sessions.
|
| 97 |
+
- Treat all simulated patients equivalently, regardless of perceived quality or style.
|
| 98 |
+
|
| 99 |
+
## Additional Comments *(Optional)*
|
| 100 |
+
|
| 101 |
+
Some questions may include an optional field for additional comments.
|
| 102 |
+
|
| 103 |
+
You may use this space to:
|
| 104 |
+
- Briefly explain your reasoning
|
| 105 |
+
- Note ambiguities or uncertainties
|
| 106 |
+
- Highlight particularly salient aspects of the patient’s portrayal
|
| 107 |
+
|
| 108 |
+
Providing comments is optional but encouraged when relevant.
|
| 109 |
+
|
| 110 |
+
---
|