What is sentiment analysis?
Sentiment analysis is the interpretation and classification of emotions in the feedback. The emotions could be positive, negative & neutral. Text analysis and natural language processing techniques help us measure emotion.
Synergita has launched this new feature to help the users analyze the sentiment when they provide feedback in the performance reviews.
Does the sentiment indicate the performance of the employee?
No. The sentiment is different from the performance ratings. Sentiment analysis will NOT impact the rating/score that managers provide. Please refer to the examples given in the below table.
How do sentiment analysis help employees and managers?
Studies show that the probability of any individual accepting the feedback constructively is more when the sentiment/emotion in the language is positive.
This new feature helps the employees & managers check the underlying emotion while providing the feedback itself. If the emotion is neutral or negative, you can rephrase the feedback to bring more positive emotion.
|“You are sometimes result-oriented. But more often the objectives are not met”||NEGATIVE|
|“You are sometimes result-oriented. You can become better if you set clear objectives for your team members. Also please keep an eye on the performance dashboard for better tracking of Objectives”||NEUTRAL|
|“You are sometimes result-oriented. You can become better if you set clear objectives for your team members. Also please keep an eye on the performance dashboard for better tracking of Objectives. These corrective actions will bring very good success for you.”||POSITIVE|
How does the system identify the sentiments?
Sentiment analysis inspects the given feedback and identifies the prevailing emotional opinion within the text, especially to determine a writer's attitude as positive, negative, or neutral.
The score of the sentiment ranges between -1.0 (negative) and 1.0 (positive) and corresponds to the overall emotional learning of the text.
Magnitude indicates the overall strength of emotion (both positive and negative) within the given text, between 0.0 and +inf. Each expression of emotion within the text (both positive and negative) contributes to the text's magnitude (so longer text blocks may have greater magnitudes)