Extracting problematic API features from forum discussions

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)?

A custom technique proposed in this paper (Haystack), uses a dictionary based approach to extract negative sentences that reference a certain feature. Sentiment analysis is done using: Sentiment140 API: A. Go, R. Bhayani, and L. Huang, “Twitter sentiment classification using distant supervision,” Stanford University, Tech. Rep., 2009.

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.

Sentiment140: http://help.sentiment140.com/

4. What is the main goal of the whole study?

Finding API features on forums about which negative sentiment has been expressed. Such that useful data can be extracted.

5. What the researchers want to achieve by applying the technique(s) (e.g., calculate the sentiment polarity of app reviews)?

Calculate the sentiment of statements made about API features, and extract the features discussed in negative sentences.

6. Which dataset(s) the technique is applied on?

33k sentences extracted from the Swing forum.

7. Is/Are the dataset(s) publicly available online? If yes, please indicate their name and links.

-

8. Is the application context (dataset or application domain) different from that for which the technique was originally designed?

Yes, sentiment technique was trained on Twitter, data are sentences from a Swing forum. However, the entire pipeline in the paper was designed for Swing forum data.

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?

Authors verify the technique by comparing the resulting features extracted by their tool, Haystack, with a manual analysis of the same data. Finding that their technique manages to identify the same topics of interest.

10. Does the paper replicate the results of previous work? If yes, leave a summary of the findings (confirm/partially confirms/contradicts).

-

11. What success metrics are used?

-

12. Write down any other comments/notes here.

-