Performance Analysis on Student Feedback using LSTM Algorithm
This study proposes aspect based sentimental analysis based on two layered LSTM model for evaluating the faculty performance. . The first layer of the model is used to find the aspect associated with the opinion being formed and the second layer which predicts the sentiment orientation of the predicted aspect. They also incorporated word embedding into these models expect that these trained domain embedding capture semantic similarities between words in a better way. To generate these domain word embedding, we should use a skip gram model..
The aim is to develop a web portal in which student who can make their reviews of teachers and from the opinion, identify the aspect associated such as six aspects including- Teaching Pedagogy, Behaviour, Knowledge, Assessment, Experience, and General comments. Next, it predicts the sentiment orientation that is positive, negative and neutral of the extracted aspect terms.
PROJECT OUTPUT VIDEO:
ALGORITHM/ MODEL USED:
- System : Pentium i3 Processor.
- Hard Disk : 500 GB.
- Monitor : 15’’ LED
- Input Devices : Keyboard, Mouse
- Ram : 4 GB
- Operating system : Windows 10.
- Coding Language : Python
- Web framework : Flask