ABSTRAT:
Students’ feedback is crucial for academic institutions in order to evaluate faculty perfor- mance. Handling the qualitative opinions of students efficiently while automatic report generation is a challenging task. Indeed, most of the organizations deal with quantitative feedback effectively, whereas qualitative feedback is either processed manually or ignored altogether. This research proposes a supervised aspect based opinion mining system based on two layered LSTM model. The first layer predicts the aspects described within the feedback and later specifies the orientation (positive, negative, neutral) of those predicted aspects. The model was tested on a manually tagged data set constructed from the last five years students’ comments from Sukkur IBA University as well as on a standard SemEval-2014 data set. Unlike many other LSTM models proposed for other domains, the proposed model is quite simple in terms of architecture which results in less complexity. The system attains good accuracy using the domain embedding layer in both tasks: aspect extraction (91%) and sentiment polarity detection (93%). To the best of our knowledge, this study is a first attempt that uses deep learning approach for performing aspect based sentiment analysis on students’ feedback for evaluating faculty teaching performance
EXISTING SYSTEM :
The second task in ABSA is to predict the orientation of aspects mentioned in the sentence.In [18] after aspect extrac- tion, opinion terms were extracted using using “10 syntactic dependency rules”. They consider those adjectives as opin- ions which are from the 3- word distance to aspect. WordNet was used to calculate polarity of extracted opinion phrase. Another study performed aspect sentiment classification on movie reviews [19]. In addition, to calculate sentiment ori- entation, they also specified sentiment strength towards a particular aspect of the movie. SentiwordNet was used as a lexical resource for computing sentiment scores
EXISTING SYSTEM DISADVANTAGES:
1.LESS ACCURACY
2. LOW EFFICIENCY
PROPOSED SYSTEM :
They concluded that the sentiment model can be used as a model of choice for teaching evaluation. The teacher’s performance evaluation tool was proposed in [32]. They classified the English and Filipino language comment in the positive and negative category based on the cumulative score of opinion terms. The scores were fetched from their own created polarity data set. They used the Naive Bayes classifier for performing the task of sentiment analysis. Various machine learning algorithms (SVM, Random Forest, Simple Logistics, Decision Tree) and one of deep learning method (multilayer perceptron) were used to perform the task of sentiment analysis on educational database [33]. The highest accuracy was achieved with SVM 78.7% and %78.3 with Multilayer Perceptron.
PROPOSED SYSTEM ADVANTAGES:
1.HIGH ACCURACY
2.HIGH EFFICIENCY
SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10
HARDWARE REQUIREMENTS:
Processor : Core I3
RAM Capacity : 2 GB
Hard Disk : 250 GB
Monitor : 15″ Color
Mouse : 2 or 3 Button Mouse
Key Board : Windows 08/10
