Customer comments within reviews and surveys are transformed into text analytic categories. These categories are grouped within the domains that are customized for your account (e.g., Staff, Transaction, Satisfaction, Experience, etc.).
Categories are then measured by category sentiment, which is a more precise measure of customer satisfaction than 1-5 star rating. This algorithm breaks down the review content into categories that are scored separately (e.g., a customer gives a 4-star on a review that raves about the polite doctor but complains about parking). The algorithm may score 100 to sentiment in "Staff" (positive) and 0 to sentiment in "Parking" (negative). After all sentences are given a score (0 negative, 50 neutral, 100 positive), each category score is added and divided by the total number of mentions for that category.
Example: 15 total mentions for Parking
5 are negative = (0x5) = 0
8 are positive = (8x100) = 800
2 are neutral = (2x50) = 100
0+800+100=900
900/15 = 60
The Parking category sentiment equals 60.
Customer comments within reviews and surveys are transformed into text analytic categories. These categories are grouped within the domains that are customized for your account (e.g., Staff, Transaction, Satisfaction, Experience, etc.).
Categories are then measured by category sentiment, which is a more precise measure of customer satisfaction than 1-5 star rating. This algorithm breaks down the review content into categories that are scored separately (e.g., a customer gives a 4-star on a review that raves about the polite doctor but complains about parking). The algorithm may score 100 to sentiment in "Staff" (positive) and 0 to sentiment in "Parking" (negative). After all sentences are given a score (0 negative, 50 neutral, 100 positive), each category score is added and divided by the total number of mentions for that category.
Example: 15 total mentions for Parking
5 are negative = (0x5) = 0
8 are positive = (8x100) = 800
2 are neutral = (2x50) = 100
0+800+100=900
900/15 = 60
The Parking category sentiment equals 60.
Customer comments within reviews and surveys are transformed into text analytic categories. These categories are grouped within the domains that are customized for your account (e.g., Staff, Transaction, Satisfaction, Experience, etc.).
Categories are then measured by category sentiment, which is a more precise measure of customer satisfaction than 1-5 star rating. This algorithm breaks down the review content into categories that are scored separately (e.g., a customer gives a 4-star on a review that raves about the polite doctor but complains about parking). The algorithm may score 100 to sentiment in "Staff" (positive) and 0 to sentiment in "Parking" (negative). After all sentences are given a score (0 negative, 50 neutral, 100 positive), each category score is added and divided by the total number of mentions for that category.
Example: 15 total mentions for Parking
5 are negative = (0x5) = 0
8 are positive = (8x100) = 800
2 are neutral = (2x50) = 100
0+800+100=900
900/15 = 60
The Parking category sentiment equals 60.
Customer comments within reviews and surveys are transformed into text analytic categories. These categories are grouped within the domains that are customized for your account (e.g., Staff, Transaction, Satisfaction, Experience, etc.).
Categories are then measured by category sentiment, which is a more precise measure of customer satisfaction than 1-5 star rating. This algorithm breaks down the review content into categories that are scored separately (e.g., a customer gives a 4-star on a review that raves about the polite doctor but complains about parking). The algorithm may score 100 to sentiment in "Staff" (positive) and 0 to sentiment in "Parking" (negative). After all sentences are given a score (0 negative, 50 neutral, 100 positive), each category score is added and divided by the total number of mentions for that category.
Example: 15 total mentions for Parking
5 are negative = (0x5) = 0
8 are positive = (8x100) = 800
2 are neutral = (2x50) = 100
0+800+100=900
900/15 = 60
The Parking category sentiment equals 60.
Customer comments within reviews and surveys are transformed into text analytic categories. These categories are grouped within the domains that are customized for your account (e.g., Staff, Transaction, Satisfaction, Experience, etc.).
Categories are then measured by category sentiment, which is a more precise measure of customer satisfaction than 1-5 star rating. This algorithm breaks down the review content into categories that are scored separately (e.g., a customer gives a 4-star on a review that raves about the polite doctor but complains about parking). The algorithm may score 100 to sentiment in "Staff" (positive) and 0 to sentiment in "Parking" (negative). After all sentences are given a score (0 negative, 50 neutral, 100 positive), each category score is added and divided by the total number of mentions for that category.
Example: 15 total mentions for Parking
5 are negative = (0x5) = 0
8 are positive = (8x100) = 800
2 are neutral = (2x50) = 100
0+800+100=900
900/15 = 60
The Parking category sentiment equals 60.
Customer comments within reviews and surveys are transformed into text analytic categories. These categories are grouped within the domains that are customized for your account (e.g., Staff, Transaction, Satisfaction, Experience, etc.).
Categories are then measured by category sentiment, which is a more precise measure of customer satisfaction than 1-5 star rating. This algorithm breaks down the review content into categories that are scored separately (e.g., a customer gives a 4-star on a review that raves about the polite doctor but complains about parking). The algorithm may score 100 to sentiment in "Staff" (positive) and 0 to sentiment in "Parking" (negative). After all sentences are given a score (0 negative, 50 neutral, 100 positive), each category score is added and divided by the total number of mentions for that category.
Example: 15 total mentions for Parking
5 are negative = (0x5) = 0
8 are positive = (8x100) = 800
2 are neutral = (2x50) = 100
0+800+100=900
900/15 = 60
The Parking category sentiment equals 60.
Customer comments within reviews and surveys are transformed into text analytic categories. These categories are grouped within the domains that are customized for your account (e.g., Staff, Transaction, Satisfaction, Experience, etc.).
Categories are then measured by category sentiment, which is a more precise measure of customer satisfaction than 1-5 star rating. This algorithm breaks down the review content into categories that are scored separately (e.g., a customer gives a 4-star on a review that raves about the polite doctor but complains about parking). The algorithm may score 100 to sentiment in "Staff" (positive) and 0 to sentiment in "Parking" (negative). After all sentences are given a score (0 negative, 50 neutral, 100 positive), each category score is added and divided by the total number of mentions for that category.
Example: 15 total mentions for Parking
5 are negative = (0x5) = 0
8 are positive = (8x100) = 800
2 are neutral = (2x50) = 100
0+800+100=900
900/15 = 60
The Parking category sentiment equals 60.