Sentiment Analysis on Reviews

Opinion mining or comments toward attitude evaluation, individual entity, are usually called sentiment. Everyone is free to give opinion related with the present opinions on youtube. Hence people have a free will to express their opinion regarding the performance. Due to the raise of many critics th

Project Title

Sentiment Analysis on Reviews

Project Area of Specialization

Computer Science

Project Summary

Opinion mining or comments toward attitude evaluation, individual entity, are usually called sentiment. Everyone is free to give opinion related with the present opinions on youtube. Hence people have a free will to express their opinion regarding the performance. Due to the raise of many critics that appear in a short amount of time, there a need to conduct a analysis on opinion mining. The process of searching or tracing the natural language to find patterns or moods of society against certain products, people or topics is called Sentiment Analysis. Sentiment analysis is also often referred to as the opinion of mining. The sentiment analysis has received considerable attention since the research of Pang, Turney, Goldberg and Zhu. Sentiment analysis techniques can support many decisions in many scenarios. In this era of life, news channels feedback is important to measure the quality of news. News channels feedback can be analyzed using to identify the news positive or negative attitude. In most of the existing news evaluation system, the intensifier words and blind negation words are not considered. The level of opinion result isn't displayed: whether positive or negative opinion. To address this problem, we propose to analyze the news text feedback automatically to predict the level of news performance. A database of English sentiment words is created as a lexical source to get the polarity of words. By analyzing the sentiment information including intensifier words extracting from news channels feedback, we are able to determine opinion result of news, describing the level of positive or negative opinions. This system shows the opinion result of channels that is represented as to whether strongly positive, moderately positive, weakly positive, strongly negative, moderately negative, weakly negative or neutral.

Project Objectives

In this project, sentiment analysis will be used to evaluate the level of news channels performance from news textual feedback comment. A database of English sentiment words is constructed to identify the polarity of words as a lexical source. Our sentiment word database contains the opinion words concerning with the academic domain to achieve the better result. Every opinion word in the database is given a value. The sentiment value will have a range. This project proposes the level of news evaluation method. This method analyzes automatically the news channel feedback comments to strongly negative, or moderately negative, or weakly negative, or strongly positive, or moderately positive, or weakly positive or neutral category using two lexicons. The level of opinion result for any channels is given out from news channel feedback comments.

Project Implementation Method

A large amount of data that is generated today is unstractured which requires processing to generate insights. Some examples of unstructured data are news articles, posts on social media, and search history. The process of analyzing natural language and making sense out of it falls under the field of Natural Language Processing (NLP). Sentiment analysis is a common NLP task, which involves classifying texts or parts of texts into a pre-defined sentiment. You will use the Natural Language Processing(NLTK) a commonly used NLP library in Python, to analyze textual data.

In this project, I will prepare a dataset of sample comments from the NLTK package for NLP with different data cleaning methods. Once the dataset is ready for processing, you will train a model on pre-classified comments and use the model to classify the sample comments into negative and positives sentiments.

1. Data Crawler
2. Data Extract 
3. Data Preprocessing
4. Data Visualization
5. Implement Natural Language Processing
6. Implement Machine Learning
7. Testing
8. Build Interface 

Benefits of the Project

• Happy customers are more likely to be receptive to upselling. With sentiment analysis, you can easily identify your happiest customers.
• This helps you recognise chatters who might be receptive to spending more, as well as avoiding upsetting disgruntled customers with any unwelcome sales pitches.

• You no doubt monitor agent efficiency. But how do you monitor agent empathy? Or emotional intelligence? In terms of your operations, one of the most helpful benefits of sentiment analysis is its utility as a performance measurement tool.

  Sentiment analysis gives you a clear overview of customer satisfaction, agent by agent. This means you can keep an eye on the quality of service each team member is offering customers, as well as their more subtle ability to create happy customers.

• The benefits of sentiment analysis go beyond helping your human agents. If you have a chatbot on your site, it can benefit from sentiment analysis too. That’s because it can train your chatbot to recognise, and respond to, customer mood.

• Emotional triggers drive our decisions. Using sentiment analysis, you can identify what messages and conversations act as emotive triggers that change customer mood.

  Perhaps the phrase “Please wait”, for example, often triggers customer annoyance. Or perhaps using emojis has a positive effect on the conversation’s overall tone.

  Understanding what messages trigger certain emotions in your customers can help you give better service, and is also useful for creating effective marketing materials.

Technical Details of Final Deliverable

• The aim of this project is facilitating news channels by providing classified news on their screens of their laptops.
• Then user will view the news of positive and negative type.
• After the successful posting of the news everyone can view the news by its rating according to it.
• Tweets: User can review his desire news.
• Classification: The news of other users related to anything will be classified according to its main positivity and its negativity and it will be easy for user to search news according to domains related to anything.
• Clustering the Tweets: News feedback from people or pages user is following will be clustered and shown on dashboard according to them are classified.
• Following: User can follow any other user people or pages he wants to follow so he can watch the desire news channel

Final Deliverable of the Project

Software System

Core Industry

IT

Other Industries

Core Technology

Others

Other Technologies

Sustainable Development Goals

Industry, Innovation and Infrastructure

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com