Use sentiment analysis in Data 360 to evaluate unstructured text and learn how customers feel about your brand, product, or service. For each record, such as a customer review or survey response, the model assigns a positive, negative, or neutral label and a confidence score. To filter audiences, build dashboards, and trigger automations, apply the model outputs.
Note
All sentiment analysis models and algorithms use the new runtime.
Use Cases
Forecasting supports various use cases.
| TYPE | USE CASE | WHAT DOES IT SOLVE |
| Marketing | Refine Campaigns | To improve messaging, analyze sentiment in campaign responses. |
| Segment Audiences | Target promoters, neutrals, and detractors differently. | |
| Track Brand Perception | Monitor how campaigns impact sentiment over time. | |
| Service | Prioritize Cases | Identify and escalate negative sentiment quickly. |
| Improve Support Quality | Analyze sentiment in interactions to coach reps. | |
| Reduce Churn | Detect unhappy customers early and trigger recovery actions. | |
| Sales | Deal Health Scoring | To gauge deal momentum, analyze sentiment in emails, call transcripts, and meeting notes. |
| Pipeline Prioritization | Focus on opportunities with sentiment that improves or remains consistently positive. | |
| Upsell and Cross-Sell | Identify satisfied customers with positive sentiment as strong expansion candidates. |
Considerations
Before you apply a sentiment analysis model, review these considerations.
- Use clean, relevant text data, such as customer reviews or case comments.
- Combine sentiment with other data, such as behavior or demographics, for better insights.
- Analyze trends over time rather than individual results.
Limitations
Before you use sentiment analysis, review these limitations.
- Short, vague, or highly technical text is difficult to interpret.
- Sarcasm and nuanced language affect accuracy.
- Results depend on the quality and context of the input data.