Can a Machine Learn Through Customer Sentiment?: A Cost-Aware Approach to Predict Support Ticket Escalations
1. Does the paper propose a new opinion mining approach?
Yes
2. Which opinion mining techniques are used (list all of them, clearly stating their name/reference)?
IBM Watson’s Natural Language Understanding (NLU) tool for analysis, which has the capability to analyze both sentiment and emotion.
3. Which opinion mining approaches in the paper are publicly available? Write down their name and links. If no approach is publicly available, leave it blank or None.
IBM Watson’s Natural Language Understanding (NLU): https://www.ibm.com/cloud/watson-natural-language-understanding
4. What is the main goal of the whole study?
They describe an approach that analyzes the emotions in conversations between a customer and a support analyst when dealing with customer support tickets to prevent ticket escalation.
5. What the researchers want to achieve by applying the technique(s) (e.g., calculate the sentiment polarity of app reviews)?
Calculate sentiments and emotion in conversations between IT customers and support analysts
6. Which dataset(s) the technique is applied on?
A dataset of of 356 support tickets, 242 (68%) escalated, and 114 (32%) not.
7. Is/Are the dataset(s) publicly available online? If yes, please indicate their name and links.
No
8. Is the application context (dataset or application domain) different from that for which the technique was originally designed?
Yes
9. Is the performance (precision, recall, run-time, etc.) of the technique verified? If yes, how did they verify it and what are the results?
The performance of the sentiment analysis is not evaluated. They evaluate the performance of the ML approach, using sentiment analysis, to predict the ticket escalation.
10. Does the paper replicate the results of previous work? If yes, leave a summary of the findings (confirm/partially confirms/contradicts).
No
11. What success metrics are used?
None for sentiment analysis.
12. Write down any other comments/notes here.
-