“…One more concern arises from the volume of the datasets used and in most cases the volume of the used dataset in previous studies was relatively small, all less than 7,000 comments, and this creates a gap to ask a question, how reliable can be the developed model which was trained with relatively small data volume. Following are number of inputs in several recent researches: 101 comments [16], 200 comments [2], 1822 comments [11], 2254 comments [5], 3000 comments [10], 3800 comments [9] and 6000+ comments [22]. One of objectives of this researches is to use a large dataset to avoid underfitting or overfitting of the model.…”