Open source software adoption evaluation through feature level sentiment analysis using Twitter data

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)?

ID3 classifier with AdaBoost

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.

None except traditional classifiers

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

To extract, analyze, and summarize the developer’s sentiment regarding various facets of the OSS such as functionality, support availability, configurability, compatibility, and reliability.

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

To collect the textual reviews regarding the software resource, assign the sentiment polarity (positive or negative) to each comment, extract the adoption aspect which the comment talks about, and then based on the adoption aspects of the software generate an aggregated sentiment profile of the software

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

1992 tweet reviews containing 1381 positive and 674 negative reviews

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?

Old classifier trained with new 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?

Yes, frequent feature extraction: Precision and recall using AdaBoost, Apriori, GSP and Bayesian sentiment analysis: Accuracy using AdaBoost, Apriori, GSP and Bayesian the new approach is effective in performing the task, having an acceptable score for precision and recall, above 80%

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?

Accuracy, Precision, Recall

12. Write down any other comments/notes here.

-