Belief Analysis of Amazon Customer Reviews with Visualizations


E-commerce has actually ended up being more popular with the development in internet and network innovations. Many individuals feel practical to purchase products online using various forums such as Amazon, Flipchart, Awok and so on. When clients purchase the items online there is an alternative for them to provide their review comments. Many customers picked to offer their experience, viewpoint, feedback and so on. Such product evaluations are abundant in details including feedback shared by users. The evaluation remarks are beneficial to both other buyers and vendors. The belief analysis of customer evaluations assists the vendor to comprehend user’s point of views. They can even more utilize the review remarks and enhance their items.

Figure 1. Belief analysis of consumer evaluation remarks

The sentiment analyzer such as VADER offers the belief score in terms of positive, negative, neutral and compound rating as displayed in figure 1. Amazon is an e-commerce website and many users provide evaluation discuss this online site. This research study focuses on belief analysis of Amazon client evaluations. The analysis is carried out on 12,500 evaluation comments. The preprocessing of reviews is carried out initially by getting rid of URL, tags, stop words, and letters are transformed to lower case letters. On each comment, the VADER sentiment analyzer is performed. The following table shows examples of evaluation comments and belief scores computed by VADER. Also, the number of positive, negative, neutral sentiment words are arranged.

3D Sentiment Visualization

Review comments on a couple of particular products are picked, and belief analysis is performed on these remarks. The evaluation comments for external USB DVDCD and GE 72887 Superadio III Portable AMFM Radio are examined. There are 199 comments for external USB DVDCD and 11,630 words. For GE 72887 Superadio III Portable AMFM Radio, 265 comments, and 33,973 words. For a provided evaluation, each word contributes to the total sentiment and it is fascinating to know the contribution of the variety of belief words to ball game. The contribution of negative and favorable words to the compound score is depicted in regards to the 3D surface area in figure 2.

Figure 2. 3D surface view of substance belief score.

In figure 2( a) the compound score for evaluation comments of external USD DVDCD as the 3D surface versus the variety of positive and unfavorable words is revealed. This 3D surface reveals the variation in the compound rating for a particular product due to the variety of negative and positive words.

In figure 3, the 3D column chart is depicted for external USB DVDCD and GE 72887 Superadio III Portable AMFM Radio. The substance rating for the evaluations is plotted as column chart against the number of favorable words along the x-axis and variety of negative words along the y-axis. Utilizing this 3D column chart the qualities of product reviews can be understood.

Figure 3. 3D column chart for substance belief rating

A review remark can be considered as a point in 3D area with coordinates as the variety of favorable, number negative and the variety of neutral words. This results in 3D area scatter plot of evaluation comments. In figure 4 the 3D scatter plot for external USB DVDCD and GE 72887 Superadio III Portable AMFM Radio are revealed. Each review is a point in this 3D space likewise offered the color of Blue for positive, Red for unfavorable and Green for neutral compound sentiment score. This 3D scatter plot represents the distribution of evaluation scores versus the number of belief words.

Figure 4. 3D scatter plot for customer evaluations.

The words having maximum belief score and minimum sentiment score can be gathered for each item. The following pie chart in figure 5 reveals the ten words with maximum positive sentiment score for external USB DVDCD and GE 72887 Superadio III Portable AMFM Radio. These are words which consumers have actually written in product reviews. The pie chart represents the most applauded part of the products by consumers. Likewise, most common words with negative sentiments will represent in review comments help vendors to improve their products.

Figure 5. Pie chart for leading 10 words.

Research Paper

The research study on belief visualization of Amazon reviews is appeared in: …

Cite the Work

Please cite the following term paper:

Siddhaling Urologin, Sunil Thomas, “3D Visualization of Sentiment Measures and Sentiment Classification utilizing Combined Classifier for Customer Product Reviews”, International Journal of Advanced Computer Science and Applications (IJACSA), Volume 9 Issue 5, pp. 60-68, June 2018.

Further Projects and Contact

For further reading and other tasks please go to

Dr. Siddhaling Urolagin,

Department of Computer Science

BITS Pilani, Dubai Campus, Academic City

Dubai, United Arab Emirates

Please follow and like us: