It's easy for people to tell whether a review is positive or negative. It's much harder for computers because they have neither feelings nor understanding. Software that leaves out objective sentences is better at the task than systems that churn through whole documents. One of the fundamental challenges in getting computers to sort and analyze text is finding ways to automatically classify information. Applications like search engines that group similar documents do so using topic-based categories. Sentiment analysis techniques add another dimension by determining the author's attitude about a topic rather than just identifying a topic.
posted by Marcus Zillman |
4:25 AM
