A little bird told me: Mining tweets for requirements and software evolution
1. Does the paper propose a new opinion mining approach?
No
2. Which opinion mining techniques are used (list all of them, clearly stating their name/reference)?
We use a lexical sentiment analysis tool specialized in short informal text, SentiStrength [27], which assigns both a positive and a negative score with ranges of [1, 5] and [-1, -5], respectively, to each tweet. 5 denotes an extremely positive and -5 an extremely negative sentiment. 1 and -1 denote the absence of positive and negative sentiment, respectively. We compute a single sentiment score for every tweet in the range of [1,9] by adding the positive and negative score and then adding 5. As tweets with low sentiment scores typically require more attention than ones containing praise, we use the inverse of the sentiment score to calculate the sentiment factor.
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.
Sentistrength: http://sentistrength.wlv.ac.uk/
4. What is the main goal of the whole study?
In this work we present ALERTme, an approach to automatically classify, group and rank tweets about software applications. We apply machine learning techniques for automatically classifying tweets requesting improvements, topic modeling for grouping semantically related tweets and a weighted function for ranking tweets according to specific attributes, such as content category, sentiment and number of retweets.
5. What the researchers want to achieve by applying the technique(s) (e.g., calculate the sentiment polarity of app reviews)?
Compute the sentiment of tweets about software applications.
6. Which dataset(s) the technique is applied on?
We ran our approach on 68,108 collected tweets from three software applications and compared its results against software practitioners’ judgement.
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?
No, Sentistrength has been originally validated on data from generalist social media.
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 Sentistrength performance is not assessed. The authors evaluate the overall approach for tweet categorization.
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?
-
12. Write down any other comments/notes here.
-