Abstract
The analysis of user-generated content on the Internet has become increasingly popular for a wide variety of applications. One particular type of content is represented by the user reviews for programs, multimedia, products, and so on. Investigating the opinion contained by reviews may help in following the evolution of the reviewed items and thus in improving their quality. Detecting contradictory opinions in reviews is crucial when evaluating the quality of the respective resource. This article aims to estimate the contradiction intensity (strength) in the context of online courses (MOOC). This estimation was based on review ratings and on sentiment polarity in the comments, with respect to specific aspects, such as “lecturer”, “presentation”, etc. Between course sessions, users stop reviewing, and also, the course contents may evolve. Thus, the reviews are time dependent, and this is why they should be considered grouped by the course sessions. Having this in mind, the contribution of this paper is threefold: (a) defining the notion of subjective contradiction around specific aspects and then estimating its intensity based on sentiment polarity, review ratings, and temporality; (b) developing a dataset to evaluate the contradiction intensity measure, which was annotated based on a user study; (c) comparing our unsupervised method with supervised methods with automatic feature selection, over the dataset. The dataset collected from coursera.org is in English. It includes 2244 courses and 73,873 user-generated reviews of those courses.The results proved that the standard deviation of the ratings, the standard deviation of the polarities, and the number of reviews are suitable features for predicting the contradiction intensity classes. Among the supervised methods, the J48 decision trees algorithm yielded the best performance, compared to the naive Bayes model and the SVM model.
Highlights
The idea of this article was to extract the opinions by aspect, to detect if there was a contradiction among the opinions on the same aspect, and to measure the intensity of this contradiction. This measure, allows the user reading the reviews to have a metric indicating if the reviews are all in the same direction, positive or negative, or if there is a large divergence of opinion on a specific aspect
In this article, the notion of diversity as the dispersion of sentiments; RQ2: How can the strength of a contradiction occurring in reviews be estimated? This was performed by computing the degree of dispersion of sentiment polarity around an aspect of a web resource; RQ3: How do we balance the sentiment polarity around an aspect and the global rating of a review leading to the underlying question, when computing the intensity of a contradiction? What is the weight of the global rating of a review in the expression of feelings around an aspect?
We studied the influence of the sentiment analysis algorithm on the results
Summary
Since the evolution of the Internet, and of the Web 2.0, where users represent content producers, it has become essential to be able to analyze the associated textual information in order to facilitate better navigation through it. The idea of this article was to extract the opinions by aspect, to detect if there was a contradiction among the opinions on the same aspect, and to measure the intensity of this contradiction This measure, allows the user reading the reviews to have a metric indicating if the reviews are all (or almost all) in the same direction, positive or negative, or if there is a large divergence of opinion on a specific aspect. The measure indicates that it is difficult to tell if this aspect is rated positively or negatively This measure enabled us to alert the user by indicating the points of disagreement present in the comments for particular aspects, highlighting the aspects for which the point of view is the most subjective to each person’s appreciation. Examples include work on fact contradiction, the detection and evaluation of controversies, disputes, scandals, the detection of viewpoints, and vandalized pages, mainly in Wikipedia
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
