Abstract
With the spread of mobile applications and online interactive platforms, the number of user reviews are increasing explosively and becoming one of the most important ways for users to voice opinions. Opinion target extraction and opinion word extraction are two key procedures used to determine the helpfulness of reviews. In this paper, we implement a system to extract “opinion target:opinion word” pairs based on the Conditional Random Field (CRF). Firstly, we used the CRF model to extract opinion targets and opinion words, then combined these into pairs in order. In addition, Node.js was used to build a visualization system to display “opinion target:opinion word” pairs. In order to verify the effectiveness of the system, experiments were conducted on the Laptop and Restaurant datasets of SemEval-2014-task4, and the accuracy of the F value extracted by the model reached 86% and 90%, respectively. All the code and datasets for this experiment are available on GitHub.
Highlights
With the popularity of mobile payment, the increasing numbers of consumers are causing the numbers of reviews of products to increase exponentially
The toolkit can automatically generate feature functions based on the input features in the training dataset, user-defined tags and templates and can calculate weights for each feature function. Through these trained feature functions, the toolkit can mark the sentences of the test dataset. This is the principle of the Conditional Random Field (CRF) model for opinion target extraction
We trained a model for “opinion target: opinion words” pair extraction based on the CRF and tested it using the SemEval-2014 Restaurant and Laptop datasets
Summary
With the popularity of mobile payment, the increasing numbers of consumers are causing the numbers of reviews of products to increase exponentially If these evaluation sentences are condensed and only the opinion target and opinion words are retained, it can help consumers to shop online, such as when booking hotels, ordering takeaways, etc., allowing users to quickly locate the information they need. The sentence “The battery life seems to be very good, and have had no issues with it; enabling the battery timer is useless.” includes two opinion targets, and each target matches one opinion word In this condition, customers could be interested in different parts of the item, so they want to obtain the key information with its corresponding evaluation rather than a single sentiment polarity score to help them learn everything about the product.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
