Hindi Sentiment Analysis Prompt for Social Media Comments

About Prompt

• Prompt Type – Dynamic
• Prompt Platform – ChatGPT, Grok, Deepseek, Gemini, Copilot, Midjourney, Meta AI and more
• Niche – Specific Language
• Language – English
• Category – Data Analysis
• Prompt Title – Hindi Sentiment Analysis Prompt for Social Media Comments

## Hindi Sentiment Analysis Prompt for Social Media Comments (Dynamic & Cross-Platform)

This prompt is designed for robust and accurate sentiment analysis of Hindi social media comments within a specific language niche. It’s dynamic, adaptable across AI platforms, and engineered for detailed, targeted analysis.

**Prompt Template:**

“`
Analyze the sentiment expressed in the following Hindi social media comment within the context of [Specific Language Niche]. Provide a comprehensive analysis encompassing the following:

**1. Input Comment:**
“`hindi
[Paste the Hindi social media comment here]
“`

**2. Specific Language Niche:** “[Specify the niche, e.g., Bollywood movies, Indian politics, Cricket, Skincare products, etc.]”

**3. Sentiment Classification:**
* Classify the overall sentiment as one of the following:
* **Strongly Positive:** Expressing strong approval, enthusiasm, or love.
* **Positive:** Expressing approval, liking, or contentment.
* **Neutral:** Expressing no strong emotional leaning, objective, or factual.
* **Negative:** Expressing disapproval, dislike, or dissatisfaction.
* **Strongly Negative:** Expressing strong disapproval, hatred, or anger.
* Provide a confidence score (0-100%) for the chosen sentiment classification. Explain briefly why this classification was chosen.

**4. Granular Sentiment Analysis (Optional, but recommended):**
* Identify specific emotions present in the comment, such as joy, sadness, anger, fear, surprise, disgust, trust, anticipation. Provide confidence scores for each identified emotion.
* If applicable, identify and explain the target of the sentiment. For example, is the comment praising a specific actor, criticizing a government policy, or expressing disappointment about a product feature?

**5. Contextual Nuances and Cultural Sensitivity:**
* Consider the cultural context and colloquialisms used in the comment. How do these factors influence the sentiment expressed? Are there any slang terms, emojis, or internet abbreviations that impact the interpretation? Explain.
* Be aware of code-mixing (e.g., Hinglish) and its impact on the sentiment.

**6. Sarcasm and Irony Detection:**
* Analyze the comment for any potential sarcasm or irony. If detected, explain how it affects the overall sentiment.

**7. Output Format:**
Provide your analysis in a structured JSON format for easy parsing and data analysis:

“`json
{
“comment”: “[Original Hindi Comment]”,
“niche”: “[Specified Language Niche]”,
“overall_sentiment”: “[Sentiment Classification]”,
“confidence_score”: [Confidence Score (0-100)],
“sentiment_explanation”: “[Explanation for Sentiment Classification]”,
“granular_sentiments”: [
{
“emotion”: “[Emotion]”,
“confidence_score”: [Confidence Score (0-100)]
},
// … more emotions
],
“sentiment_target”: “[Target of the sentiment]”,
“contextual_nuances”: “[Explanation of cultural context and colloquialisms]”,
“sarcasm_irony”: “[Explanation of detected sarcasm/irony]”,
}
“`
“`

**Example Usage:**

Let’s say your niche is “Bollywood Movies.” You encounter the following comment:

“`hindi
फिल्म तो एकदम धमाकेदार थी! क्या गाने हैं, क्या एक्टिंग है! 💯 🔥
“`

**Prompt Instance:** (Using the template above)

“`
… (Template as above) …

**1. Input Comment:**
“`hindi
फिल्म तो एकदम धमाकेदार थी! क्या गाने हैं, क्या एक्टिंग है! 💯 🔥
“`

**2. Specific Language Niche:** “Bollywood Movies”

… (Rest of the template) …
“`

**Expected Output (Example JSON):**

“`json
{
“comment”: “फिल्म तो एकदम धमाकेदार थी! क्या गाने हैं, क्या एक्टिंग है! 💯 🔥”,
“niche”: “Bollywood Movies”,
“overall_sentiment”: “Strongly Positive”,
“confidence_score”: 95,
“sentiment_explanation”: “The use of words like ‘धमाकेदार’ (fantastic), along with enthusiastic exclamations and positive emojis (💯, 🔥) clearly indicate strong positive sentiment towards the movie.”,
“granular_sentiments”: [
{
“emotion”: “Joy”,
“confidence_score”: 90
},
{
“emotion”: “Excitement”,
“confidence_score”: 85
}
],
“sentiment_target”: “The movie (implied)”,
“contextual_nuances”: “The use of colloquial Hindi and emojis reinforces the enthusiastic tone common in online movie reviews.”,
“sarcasm_irony”: “No sarcasm or irony detected.”
}
“`

**Prompt Engineering Best Practices Implemented:**

* **Clarity and Specificity:** The prompt is detailed and provides clear instructions for sentiment analysis.
* **Context Setting:** The “Specific Language Niche” parameter ensures accurate analysis within the desired domain.
* **Structured Output:** The JSON format makes it easy to process and analyze the results programmatically.
* **Granular Analysis:** The prompt encourages in-depth analysis beyond simple positive/negative classification.
* **Cultural Sensitivity:** The prompt explicitly addresses the importance of considering cultural context and colloquialisms.
* **Sarcasm/Irony Detection:** The prompt encourages AI to detect and interpret these complex language features.
* **Dynamic Template:** The template can be easily adapted for different comments and niches.
* **Cross-Platform Compatibility:** The prompt structure and JSON output format are compatible with most AI platforms.

This detailed and dynamic prompt enhances the accuracy and depth of Hindi sentiment analysis, making it a valuable tool for data analysis related to social media comments. Remember to adapt the `[placeholders]` to your specific needs.