“Expresses-an-opinion-about”: using corpus statistics in an information extraction approach to opinion mining

摘要

We present a technique for identifying the sources and targets of opinions without actually identifying the opinions them-selves. We are able to use an informa-tion extraction approach that treats opin-ion mining as relation mining; we iden-tify instances of a binary “expresses-an-opinion- about” relation. We find that we can classify source-target pairs as be-longing to the relation at a performance level significantly higher than two relevant baselines. This technique is particularly suited to emerging approaches in corpus-based so-cial science which focus on aggregating interactions between sources to determine their effects on socio-economically sig-nificant targets. Our application is the analysis of information technology (IT) innovations. This is an example of a more general problem where opinion is expressed using either sub- or supersets of expressive words found in newswire. We present an annotation scheme and an SVM-based technique that uses the lo-cal context as well as the corpus-wide frequency of a source-target pair as data to determine membership in “expresses-an- opinion-about”. While the presence of conventional subjectivity keywords ap-pears significant in the success of this technique, we are able to find the most domain-relevant keywords without sacri-ficing recall.