ABSTRACT

 The main thrust of this study is to investigate on Opinion mining for fountain university Case study of Gbadun emi e cafeteria This study focuses on enabling Gbadun emi e cafeteria analyse student of fountain university feedback to understand the student of fountain university opinion about their service being offered. The previous strategies used to capture feedback include the use of notes and the “One click feedback” strategy that requires a student of fountain university to rank or rate the service. In this research, real time analysis of student of fountain university feedback is achieved through the utilisation of a hybrid model that incorporates both the supervised and the unsupervised machine learning techniques. This hybrid model relies on the Lexicons and the use of Naïve Bayes Machine learning that assumes that every feature and each word in a review being classified is independent of any other feature. The data is first extracted from Twitter, then subjected to a SOCAL algorithm that generates a semantic orientation of either positive, negative or neutral of a given opinion or feedback. Once the semantic orientation is done, the data is divided into two sets; a training set and a test set. The training set is used train the Naïve Bayes model to classify texts and it was composed positive and negative reviews. A gold standard dataset  was then used to evaluate and measure the accuracy, precise, recall and F1 score of the hybrid model. This research also explored the performance of the lexicons and the Naïve Bayes Models separately to ascertain the performance of Hybrid model in comparison to the two models. The results show that in all the evaluation tests done on the hybrid model scored higher. On the accuracy, the hybrid model scored 67.27% which showed a higher degree of accuracy than the Lexicons and the Naïve Bayes models by 4% points. The same also applied to the precision and recall where the hybrid model scored 66.99% for precision and 66.57% for recall which was higher by 3.53 and 4.6 percentage points respectively. The F1 score on the other hand gave a score of 66.78%. Based on the above results, it is concluded that the hybrid model is best fit to be used for sentiment analysis due to its higher accuracy, precision, recall and F1 scores than the Lexicons and the Naïve Bayes when implemented separately. However further improvements on the above scores can be explored by use of ensembles where several models are combined through the use of boosting or bagging methods to smooth out predictions and combine them into one hybrid model with a best fit.

CHAPTER ONE

INTRODUCTION

Background of the Study

Opinion mining, or sentiment analysis, is a text analysis technique that uses computational linguistics and natural language processing to automatically identify and extract sentiment or opinion from within text (positive, negative, neutral, etc.). It allows you to get inside your customers’ heads and find out what they like and dislike, and why, so you can create products and services that meet their needs. When you have the right tools, you can perform opinion mining automatically, on almost any form of unstructured text, with very little human input needed.

Opinion mining and sentiment analysis models can focus on polarity of opinion (positive, negative, neutral), personal feelings (angry, happy, sad, etc.), and intentions or objectives (interested or not interested).

This study explores opinion mining using supervised learning algorithms to find the polarity of the student feedback based on pre-defined features of teaching and learning. The study conducted involves the application of a combination of machine learning and natural language processing techniques on student feedback data gathered from module evaluation survey results of fountain university Case study of Gbadun emi e cafeteria. In addition to providing a step by step explanation of the process of implementation of opinion mining from student comments using the open source data analytics tool Rapid Miner, this paper also presents a comparative performance study of the algorithms like SVM, Naïve Bayes, K Nearest Neighbor and Neural Network classifier. The data set extracted from the survey is subjected to data preprocessing which is then used to train the algorithms for binomial classification. The trained models are also capable of predicting the polarity of the student comments based on extracted features like examination, teaching etc. The results are compared to find the better performance with respect to various evaluation criteria for the different algorithms.

Statement of the Problem

Through the years, research has shown that the main challenge facing most students has been real time identification and resolving of student issues. The methods currently being used to measure student of fountain university satisfaction are slow and student of fountain university issues are identified long after the student of fountain university has left. Further due to increased use of social media and other content review sites, information has increased and analysis of such has become hectic.

Most of the feedback received is at document level whereby a scaling system is used to determine the level of satisfaction of its clients. Gbadun emi e cafeteria have implemented a five star rating technique to capture student of fountain university sentiments and provided a contact number and email through which students can leave their opinions. This method has many challenges as one would not be able to have the exact details of one‟s opinion. It gives a general view that may not really assist in decision making in terms of improvement of student of fountain university experience.

Objectives of the study

 This research is geared towards addressing the issues of Opinion mining for fountain university Case study of Gbadun emi e cafeteria Prompt users for their feedback in relation to the services received.

Specific objectives of the study are;

1. Identify and extract relevant aspects and features within the feedback.
2. It will also identify key issues that identify the opinion words and
3. Determine the orientation of the
4. Generate graphs and charts that will aid in decision making

Scope of the Study

The research will identify, design and develop a model and classifier to effectively analyse student of fountain university feedback. A prototype will then be developed to analyse the efficacy of the model. It will have the following capabilities:

Significance of the study

 Statistics have shown that Gbadun emi e cafeteria are the most frequented place in fountain university. Thus the need to have a well organized and automated way of acquiring student of fountain university feedback. The proposed system will assist in improving student of fountain university feedback acquisition and analysis and therefore aid in decision making. This will in turn improve the efficiency and effectiveness in provision of service delivery to its student of fountain universitys.

Research Questions

1. Which technologies and models are currently in place for analysing student of fountain university feedback?
2. Which is the best model for analysing student of fountain university feedback at Gbadun emi e cafeteria.
3. How can the above model be designed and
4. How can one analyse and evaluate the effectiveness of the above