| W14-2608 | meta-data from Amazon , namely the | product rating | of the reviewer . This leads |
| W06-1650 | review , its unigrams , and its | product rating | . Semantic features like mentions |
| W06-1650 | review , its uni - grams , and its | product rating | . 2 Relevant Work The task of |
| N13-2011 | review length , review unigrams and | product rating | statistics performed best . Along |
| W06-1650 | a score of 23 % . The explicit | product rating | , such as Stars is also an indicator |
| W06-1650 | automatic methods for assessing | product ratings | , e.g. , ( Pang and Lee 2005 |
| W06-1650 | the correlation we find between | product rating | and the helpfulness of the review |
| W06-1650 | 2005 ) have studied prediction of | product ratings | , which may be particularly relevant |
| W06-1650 | support the use of the raw counts of | product ratings | ( stars ) rather than the distance |
| N13-2011 | product type moderates both the | product ratings | and review length on the perceived |
| N13-2011 | descriptive statistics of the | product ratings | ( Kim et al. , 2006 ) ; the domain-specific |
| D09-1017 | of free-style texts as well as | product ratings | prepared by general users , which |
| E09-1059 | INTENSITY ) , reflecting the overall | product rating | ( MISMATCH ) , and covering a |
| W06-1650 | reviews also collect some form of | product rating | ( e.g. , Amazon.com , Over - |
