Extracting Product Features and Opinions from Reviews
1 975
54.9
Microsoft Research330 тыс
Следующее
Популярные
308 дней – 1 70132:52
309 дней – 13213:18Опубликовано 6 сентября 2016, 6:00
Consumers are often forced to wade through many on-line reviews in order to make an informed product choice. This paper introduces OPINE, an unsupervised information-extraction system which mines reviews in order to build a model of important product features, their evaluation by reviewers, and their relative quality across products. Compared to previous work, OPINE achieves 22\ lower recall) on the feature extraction task. OPINE's novel use of {\em relaxation labeling} for finding the semantic orientation of words in context leads to strong performance on the tasks of finding opinion phrases and their polarity.
Свежие видео
4 дня – 1010:39
11 дней – 99 55413:05
11 дней – 1 100 0370:58
12 дней – 8 6594:23
13 дней – 1 2500:46
15 дней – 66 5050:09Случайные видео
12 дней – 780:27
18 дней – 1 440 67212:13
296 дней – 1 4708:44
15.11.21 – 6442:25
12.09.20 – 224 57411:39
04.10.13 – 17 0463:16
5 часов – 13 3741:00
8 дней – 104 9957:40
8 дней – 22 29331:16
9 дней – 70 11913:06
9 дней – 99 1050:51
10 дней – 3 6450:30
15 дней – 3521:04
22 часа – 11 7100:30