You are an expert in NLP and conversational analysis. Your task is to evaluate the given conversation based on specific categories and return structured JSON data with predefined options for easier post-processing.

---

### **Input Format**
You will receive a conversation in the following format:
```json
[
  {"content": "User message", "role": "user"},
  {"content": "Assistant response", "role": "assistant"},
  ...
]

Evaluation Categories

Analyze the conversation and categorize it using the predefined values for each dimension.
1. Top 3 Topics

Select up to 3 topics that are most relevant to the conversation from the following list:

["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"]

    The first topic should be the most dominant in the conversation.
    The second and third topics should reflect other significant themes in the discussion.
    If a conversation only has one or two clear topics, leave the remaining slots empty.

2. Language Style of the Prompt

    "Formal"
    "Informal"
    "Mixed"

3. Grammar & Slang in User Input

    "Perfect" (No mistakes, professional style)
    "Minor Errors" (Small grammar/spelling mistakes, but understandable)
    "Major Errors" (Frequent grammar mistakes, difficult to read)
    "Contains Slang" (Uses informal slang expressions)

4. Context Awareness

    "Excellent" (Understands multi-turn context well)
    "Good" (Mostly keeps context, with minor slips)
    "Average" (Some loss of context, but overall understandable)
    "Weak" (Frequently forgets context or contradicts previous responses)
    "None" (Does not retain context at all)

5. Logical Progression of Conversation

    "Strong" (Ideas build logically and naturally)
    "Moderate" (Mostly logical but with some jumps)
    "Weak" (Frequent topic shifts or unnatural flow)

6. Topic Shifts

    "None" (Stays on the same topic)
    "Minor" (Small, relevant diversions)
    "Major" (Significant change in topic mid-conversation)

7. Type of Instruction Given to Assistant

Choose one of the following categories:

    Content Generation → User asks for creative content, including writing, design ideas, or brainstorming responses.
        Example: "Create a t-shirt design about animal rights."
        Example: "Write a short sci-fi story."
        Example: "Generate ideas for a marketing slogan."

    Factual Inquiry → User requests objective facts, statistics, or comparisons with clear, verifiable answers.
        Example: "What are the top 5 largest animal rights organizations?"
        Example: "Give me statistics on deforestation and animal extinction."
        Example: "Compare the environmental impact of cotton vs. synthetic fabrics."

    Opinion-Seeking → User explicitly asks for subjective input, recommendations, or an evaluative stance.
        Example: "What’s your opinion on using synthetic leather?"
        Example: "Do you think my t-shirt design idea is effective?"
        Example: "What’s the best way to convince people to care about animal rights?"

    Task-Oriented → User asks for structured assistance, edits, refinements, or summarization of existing content.
        Example: "Summarize the key points from this discussion."
        Example: "Improve my t-shirt design by making it more dynamic."
        Example: "Make my speech more persuasive."

    Conversational Engagement → User initiates casual, open-ended dialogue with no clear task or goal.
        Example: "What do you think about animal welfare?"
        Example: "Tell me something interesting about t-shirts!"
        Example: "Let’s chat about animal rights history."

Output Format

Return a structured JSON object as follows:

{
  "topics": ["Education", "Science", "Ethics"],
  "language_style": "Formal",
  "grammar_slang": "Perfect",
  "context_awareness": "Excellent",
  "logical_progression": "Strong",
  "topic_shifts": "Minor",
  "instruction_type": "Factual Inquiry"
}

Instructions

    Select up to 3 most relevant topics, ordered by prominence in the conversation.
    Ensure responses use only predefined options for consistency in post-processing.
    Do not add explanations—only return JSON.