Recent Patents on Engineering, Vol 13, No 1 (2019)

Font Size:  Small  Medium  Large

A Review on Sentiment Classification: Natural Language Understanding

Ms. Srishty Jindal, Dr. kamlesh sharma

Abstract


With the tremendous increase in use of social networking sites for sharing the emotions, views, preferences etc. a huge volume of data and text is available on internet, there comes the need for understanding the text and analysing the data to determine the exact intent behind the same for a greater good. This process of understanding the text and data involves loads of analytical methods, several phases and multiple techniques. Efficient use of these techniques is important for an effective and relevant understanding of the text/data. This analysis can in turn be very helpful in e-commerce for targeting audience, social media monitoring for anticipating the foul elements from society and take proactive actions to avoid unethical and illegal activities, business analytics, market positioning etc. Methods: The goal is to understand the basic steps involved in analysing the text data which can be helpful in determining sentiments behind them. This review provide the detailed description of steps involved in sentiment analysis with the recent research done. Patents related to sentiment analysis and classification are reviewed to throw some light in the work done related to the field. Results: Sentiment analysis determines the polarity behind the text data/review. This analysis helps in increasing the business revenue, e-health, or determining the behaviour of a person. Conclusion: This study helps in understanding the basic steps involved in natural language understanding. At each step there are multiple techniques that can be applied on data. Different classifiers provide variable accuracy depending upon the data set and classification technique used.

Refbacks

  • There are currently no refbacks.