About Prompt
- Prompt Type – Dynamic
- Prompt Platform – ChatGPT, Grok, Deepseek, Gemini, Copilot, Midjourney, Meta AI and more
- Niche – Sentiment Analysis
- Language – English
- Category – Employee Experience
- Prompt Title – AI Prompt for Analyzing Employee Sentiment from Internal Communication
Prompt Details
**Purpose:** To analyze employee sentiment from internal communication data for enhancing employee experience.
**Prompt Type:** Dynamic
**Platform Compatibility:** All AI Platforms
**Input Data Format:** Provide the communication data in a structured format. Each entry should include:
* `timestamp`: Date and time of the communication (ISO 8601 format, e.g., YYYY-MM-DDTHH:mm:ssZ).
* `channel`: Source of the communication (e.g., Slack, email, survey, internal forum).
* `sender_id`: Unique identifier of the sender (e.g., employee ID, anonymized ID).
* `receiver_id`: Unique identifier of the receiver (can be null for broadcasts). This could be an individual or a group/channel ID.
* `message`: The actual communication content (text).
* `context` (Optional): Additional context such as the subject line of an email or the topic of a forum thread.
**Example Input Data (JSON):**
“`json
[
{
“timestamp”: “2024-07-27T10:00:00Z”,
“channel”: “Slack”,
“sender_id”: “user123”,
“receiver_id”: “channel456”,
“message”: “This new project is really exciting! Looking forward to collaborating with everyone.”,
“context”: “Project Kickoff Discussion”
},
{
“timestamp”: “2024-07-27T11:30:00Z”,
“channel”: “Email”,
“sender_id”: “user456”,
“receiver_id”: “user789”,
“message”: “I’m feeling overwhelmed with the current workload. Can we discuss prioritizing tasks?”,
“context”: “Project Update Request”
}
]
“`
**Prompt Template:**
“`
Analyze the provided employee communication data to understand prevailing sentiment trends.
**Data:**
“`json
{{input_data}}
“`
**Instructions:**
1. **Sentiment Classification:** Classify the sentiment expressed in each `message` as one of the following:
* **Positive:** Expressing optimism, satisfaction, enthusiasm, or gratitude.
* **Negative:** Expressing frustration, dissatisfaction, concern, anger, or disappointment.
* **Neutral:** Expressing factual information or lacking clear emotional expression.
2. **Sentiment Score (Optional):** If possible, provide a sentiment score for each message on a scale of -1 (most negative) to +1 (most positive), where 0 represents neutral sentiment.
3. **Trend Analysis:** Identify key sentiment trends over time. Consider factors like:
* **Changes in overall sentiment:** Are there noticeable shifts in the average sentiment score over time (e.g., increasing negativity, growing positivity)?
* **Sentiment by channel:** Are certain communication channels associated with more positive or negative sentiment?
* **Sentiment by context:** Are there specific topics or projects that are correlated with particular sentiment patterns?
4. **Key Themes and Drivers:** Extract prominent themes and potential drivers of sentiment. For example:
* Are there recurring keywords or phrases associated with positive or negative sentiment?
* Are specific events, projects, or policies mentioned in connection with sentiment shifts?
5. **Actionable Insights:** Based on the analysis, provide specific and actionable insights for improving employee experience. Examples include:
* Addressing negative sentiment related to specific workloads or processes.
* Promoting positive communication practices within specific teams or channels.
* Identifying opportunities to improve communication and transparency around specific initiatives.
**Output Format:**
Provide the analysis in a structured format, preferably JSON. Include:
* `sentiment_summary`: Overall sentiment distribution (e.g., percentage of positive, negative, and neutral messages).
* `sentiment_trends`: Summary of identified trends (e.g., changes over time, by channel, by context).
* `key_themes`: List of prominent themes associated with different sentiments.
* `actionable_insights`: List of specific and actionable recommendations.
**Example Output (Partial):**
“`json
{
“sentiment_summary”: {
“positive”: 45,
“negative”: 25,
“neutral”: 30
},
“sentiment_trends”: {
“overall”: “Slight increase in negative sentiment over the past two weeks”,
“by_channel”: “Slack messages generally more positive than emails”,
“by_context”: “Project X discussions show a significant increase in negative sentiment”
},
// … other sections
}
“`
**Additional Notes:**
* **Customization:** Adapt this prompt by adding specific keywords, topics, or aspects relevant to your organization’s context.
* **Data Privacy:** Ensure the input data is anonymized or pseudonymized to protect employee privacy.
* **Iterative Refinement:** Experiment with different phrasing and prompts to optimize the results. You might need to iterate on the prompt based on the quality of the output you are receiving.
This detailed prompt provides a comprehensive framework for analyzing employee sentiment from internal communication. By following these instructions and adapting the prompt to your specific needs, you can gain valuable insights for enhancing employee experience.
“`