{ "raw_reviews": 900000, "after_removing_short": 876636, "after_removing_duplicates": 858970, "label_distribution": { "positive": 694266, "negative": 95905, "neutral": 68799 }, "split_sizes": { "train": 72000, "val": 9000, "test": 9000, "real_world": 10000, "sandisk": 4902, "generic": 96 }, "split_labels": { "train": { "positive": 24000, "negative": 24000, "neutral": 24000 }, "val": { "positive": 3000, "negative": 3000, "neutral": 3000 }, "test": { "positive": 3000, "negative": 3000, "neutral": 3000 }, "real_world": { "positive": 8106, "negative": 1146, "neutral": 748 }, "sandisk": { "positive": 4436, "negative": 324, "neutral": 142 }, "generic": { "positive": 53, "negative": 43 } } }