How do I use the "Perform Sentiment Analysis on Dataset" prompt?

Copy the prompt template, fill in the variables (DATA_TYPE, DATA_SOURCE, SAMPLE_SIZE, DOMAIN, ANALYSIS_PURPOSE, DATASET_ENTRIES), and paste it into ChatGPT, Claude, or Gemini.

What AI tools work with this data prompt?

This prompt works with chatgpt, claude, gemini. Simply copy and paste the template into any of these AI assistants.

Tips for getting the best results?

Provide clear context about your dataset's domain and source for more accurate analysis Include sample entries that represent the variety in your dataset (different lengths, styles, topics) Specify if your data contains domain-specific jargon or slang that might affect sentiment interpretation For large datasets, start with a smaller sample to validate the analysis approach before scaling Consider providing examples of edge cases (sarcasm, mixed sentiment) you want special attention on

data advanced

Perform Sentiment Analysis on Dataset

Advanced AI prompt to analyze sentiment in datasets. Get detailed classification, confidence scores, and insights from your text data.

Works with: chatgptclaudegemini

Prompt Template

You are an expert data scientist specializing in natural language processing and sentiment analysis. I need you to perform comprehensive sentiment analysis on a dataset containing [DATA_TYPE]. Dataset Context: - Data source: [DATA_SOURCE] - Sample size: [SAMPLE_SIZE] - Target audience/domain: [DOMAIN] - Analysis purpose: [ANALYSIS_PURPOSE] For each text entry, provide: 1. Primary sentiment classification (Positive, Negative, Neutral) 2. Confidence score (0-1 scale) 3. Secondary emotion detection (joy, anger, fear, sadness, surprise, disgust) 4. Key sentiment indicators (specific words/phrases driving the classification) 5. Intensity level (Low, Medium, High) Additionally, after analyzing all entries, provide: - Overall sentiment distribution summary - Most frequent positive/negative keywords - Patterns or trends observed - Data quality assessment (ambiguous cases, potential misclassifications) - Recommendations for model improvement or data preprocessing Format your analysis as structured data that can be easily exported to CSV or JSON. Handle edge cases like sarcasm, mixed sentiment, and domain-specific language appropriately. If you encounter unclear cases, flag them for manual review. Dataset entries to analyze: [DATASET_ENTRIES]

Variables to Customize

[DATA_TYPE]

Type of text data being analyzed

Example: customer reviews for e-commerce products

[DATA_SOURCE]

Where the data originated from

Example: Amazon product reviews scraped from electronics category

[SAMPLE_SIZE]

Number of entries in the dataset

Example: 500 reviews

[DOMAIN]

Industry or subject area context

Example: consumer electronics and gadgets

[ANALYSIS_PURPOSE]

Goal of the sentiment analysis

Example: identifying product improvement opportunities and customer satisfaction trends

[DATASET_ENTRIES]

The actual text data to analyze

Example: 1. 'This phone is amazing! Battery lasts all day.' 2. 'Terrible quality, broke after one week.' 3. 'Decent product for the price, nothing special.'

Example Output

**SENTIMENT ANALYSIS RESULTS** **Individual Entry Analysis:** Entry 1: "This phone is amazing! Battery lasts all day." - Primary Sentiment: Positive (Confidence: 0.92) - Secondary Emotion: Joy - Key Indicators: "amazing", "lasts all day" - Intensity: High Entry 2: "Terrible quality, broke after one week." - Primary Sentiment: Negative (Confidence: 0.95) - Secondary Emotion: Anger - Key Indicators: "terrible", "broke" - Intensity: High Entry 3: "Decent product for the price, nothing special." - Primary Sentiment: Neutral (Confidence: 0.78) - Secondary Emotion: None - Key Indicators: "decent", "nothing special" - Intensity: Low **Summary Statistics:** - Positive: 33.3% (1 entry) - Negative: 33.3% (1 entry) - Neutral: 33.3% (1 entry) **Key Insights:** - Top positive keywords: amazing, lasts - Top negative keywords: terrible, broke - Pattern: Quality and durability are primary concern drivers - Flagged cases: None requiring manual review **Recommendations:** - Focus on product durability messaging - Monitor quality control processes - Consider price-value positioning strategies

Pro Tips for Best Results

Provide clear context about your dataset's domain and source for more accurate analysis
Include sample entries that represent the variety in your dataset (different lengths, styles, topics)
Specify if your data contains domain-specific jargon or slang that might affect sentiment interpretation
For large datasets, start with a smaller sample to validate the analysis approach before scaling
Consider providing examples of edge cases (sarcasm, mixed sentiment) you want special attention on