We've updated our privacy policy to comply with Europe's General Data Protection Regulation (GDPR), the EU-U.S. Privacy Shield, and the Swiss-U.S. Privacy Shield.. View our HR Data Privacy Policy and Non-HR Data Privacy Policy to learn more about these changes.


Sentiment Analysis of Product Reviews in the Absence of Labelled Data using Supervised Learning Approaches

With the growing pace of internet usage, there is a vast variety of diverse individual opinions and thoughts available online. Consumer reviews can act as a feedback and as well as a pool of ideas for which they can be of immense importance to any business. With the growth and popularity of opinion-rich resources such as online review sites and personal blogs, people now can and do, actively use information technology to seek out and understand the opinions of others to decide whether to buy a product or not.

Social media websites such as Facebook, Twitter, and e-commerce websites such as eBay, Amazon, etc. are being widely used to communicate viewpoints effectively. Assigning a positive or a negative sentiment to these reviews can help companies understand their users and also help users to make better decisions.

Sentiment analysis here, being a challenging task can be tackled using supervised machine learning techniques or through unsupervised lexicon based approaches if labelled data is unavailable.

Thus, the study by (Muhammad, Mushtaq, Junejo, & Khan, 2019) depicts that in absence of labelled product reviews of a particular website, labelled product reviews from a different website can be effectively used to train the supervised techniques to achieve a comparable performance to the unsupervised lexicon based approaches. This approach also benefits by covering all of the product reviews which the lexicon based approaches fail to do so. This was deduced by comparing five supervised approached and three lexicon based approaches on iPhone 5s reviews gathered from Amazon, Facebook, and Reevoo blog.

Furthermore, it was also found that unigram features combined with bigram features give the best results, and the effect of varying the training data size on the performance of ML classifiers in some cases was significant whereas in other cases it did not have any effect. The results also suggest that reviews from Amazon are easiest to classify, followed by reviews from Reevo, and Facebook reviews are the hardest to classify.

life @ ibex.

Bring People

Let's Talk

Want to learn more about how CLX can help your brand add more customers, keep more customers, and drive new revenue growth? Fill out the form to the right, and we’ll get back to you as soon as we can.

Office Locations

  • Canada
  • Jamaica
  • Nicaragua
  • Pakistan
  • Philippines
  • Senegal
  • United Kingdom
  • United States

Contact form

From clicks to conversions to lifelong customers, all with CLX

CLX is everything you need for superior customer acquisition, engagement, and growth,
together in one seamless package.


Sentiment Analysis of Product Reviews in the Absence of Labelled Data using Supervised Learning Approaches

Refer a friend

Candidate Information

Sentiment Analysis of Product Reviews in the Absence of Labelled Data using Supervised Learning Approaches

Check Status

Follow the status of your application by entering details in the box below.