Reviewer has chosen not to be AnonymousOverall Impression:
AcceptTechnical Quality of the paper:
Clear noveltyData availability:
All used and produced data (if any) are FAIR and openly available in established data repositoriesLength of the manuscript:
The length of this manuscript is about right
Summary of paper in a few sentences (summary of changes and improvements for
second round reviews):
This is a revision of a paper developing a rather detailed model of sarcasm detection.
Reasons to accept:
I feel that nearly all of my concerns about the first draft have been adressed and the paper has become much more reproducible. I congratulate the authors from the substantial improvements made.
Reasons to reject:
The only issues lingering I see is the following:
* Starting on page 2 or so the authors' literature review reports a bunch of accuracy and f-score numbers from unrelated corpora. As I said in my initial review, these are misleading and should be removed since the authors develop their own corpus. These prior results are uninformative---in fact misleading---and there's no obvious way to put them in context of the current paper, short of having the authors run their system on these corpora.