Improving the Detection of Comparison Arguments in Product Reviews
نویسنده
چکیده
A common way to express sentiment about some product in a review is by comparing it to a different product. In order to get meaningful information about the comparison, we need to identify the separate parts: the predicate that expresses the comparison, the two compared entities, and the aspect that they are compared in. In this work, we assume the sentence and the predicate to be given and work on argument identification and classification. We show that syntax is more helpful than context for the task. We also improve performance on argument identification by including information about the type of the comparison. We were not able to prove our hypothesis that including information on the sentiment of the predicate improves performance on argument classification.
منابع مشابه
Detection of Product Comparisons - How Far Does an Out-of-the-Box Semantic Role Labeling System Take You?
This short paper presents a pilot study investigating the training of a standard Semantic Role Labeling (SRL) system on product reviews for the new task of detecting comparisons. An (opinionated) comparison consists of a comparative “predicate” and up to three “arguments”: the entity evaluated positively, the entity evaluated negatively, and the aspect under which the comparison is made. In use...
متن کاملMining Interesting Aspects of a Product using Aspect-based Opinion Mining from Product Reviews (RESEARCH NOTE)
As the internet and its applications are growing, E-commerce has become one of its rapid applications. Customers of E-commerce were provided with the opportunity to express their opinion about the product on the web as a text in the form of reviews. In the previous studies, mere founding sentiment from reviews was not helpful to get the exact opinion of the review. In this paper, we have used A...
متن کاملThe Perception of Usefulness: Iranian Customers’ Evaluation of Customer Reviews
Over the last decade, the retail industry has had a phenomenal growth. All figures show their success and efficiency and many studies have shown the role of customer reviews in encouraging ambivalent purchasers to buy items online. There have been numerous studies on why people read and trust these comments and taking for granted the important role of customer reviews in determining buying deci...
متن کاملImproving Accuracy in Intrusion Detection Systems Using Classifier Ensemble and Clustering
Recently by developing the technology, the number of network-based servicesis increasing, and sensitive information of users is shared through the Internet.Accordingly, large-scale malicious attacks on computer networks could causesevere disruption to network services so cybersecurity turns to a major concern fornetworks. An intrusion detection system (IDS) could be cons...
متن کاملIdentifying Consumers' Arguments in Text
Product reviews are a corpus of textual data on consumer opinions. While reviews can be sorted by rating, there is limited support to search in the corpus for statements about particular topics, e.g. properties of a product. Moreover, where opinions are justified or criticised, statements in the corpus indicate arguments and counterarguments. Explicitly structuring these statements into argumen...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2014