Review Comment:
I would like to thank the Authors for thoroughly addressing all the points I had mentioned in my previous report. I only have one follow-up question that is given below, together with minor points/typos to be double-checked before publication.
As already said in my previous report, given its content, quality and timeliness, I do recommend this manuscript for publication in the Semantic Web journal.
-----------------------------------------------------------------------------------------------
- Clarification needed in Table 3 and related text
Please add the used value of max_support_word. I guess it is 8000 (by comparing with Table 4), but then I do not see why the results in columns 2 and 3 of Table 3 differ (e.g, 6901 vs 6478 for min_support=10). Please clarify.
In fact, from the text I understand that the only difference between ToPMine and ToPMine_max is the use of max_support_word, and that (for the current corpus) this parameter has no effect if set to 8000.
["We also defined a maximum support threshold max_support_word and call the system that uses this additional threshold TopMine_max."
"Note that no word occurs more than 8000 times in our corpus, so setting max_support_word to 8000 allows all words (or, in other words, max_support_word is not used)."]
- Other minor points/typos:
-- In Table 6, row 8: "Artificial Intelligence-Methods (NO)". Please check and in case clarify what "NO" means here.
-- Figure 16: From the values shown, I think the algorithm "with stemming" is used. In case, please specify it in the caption and text.
-- Appendix: please double check that the title and contents of the listings match.
E.g., in Listing 9: the listing seems to duplicate the following one. Some lines (including 11-14) should be removed.
E.g., in Listing 11: please double check the title, namely: "filter condition is complex that needs to be simplified".
|