click here to download the abstract project of evaluation project
click here to download the Base paper of evaluation project
ABSTRACT
The current way of checking subjective papers is adverse. Evaluating the Subjective Answers is a critical task to perform. When a human being evaluates anything, the quality of evaluation may vary along with the emotions of Person. In Machine Learning, all results are only based on the input data provided by the user. Our proposed system uses machine learning and NLP to solve this problem. Our Algorithm performs a task like Tokenizing words and sentences, Part of Speech tagging, chunking, lemmatizing words and WordNet ting to evaluate the subjective answer. Along with it, our proposed algorithm provides the semantic meaning of the context. Our System is divided into two modules. The first one is extracting data eva. lunation project, evaluation project.
from the uploaded answer documents and organizing it in the proper manner and the second is applying ML and NLP to the text retrieved from the above step and giving marks to them. The main purpose of this project is to reduce man power. The software will take a scanned document of the answer as an input and
then after the preprocessing step it will extract the text of the answer. This text will again go through processing and build a model of keywords and feature sets. The evaluator also provides the model answer sets, keywords and question specific things. The Model answer sets and keywords are categorized as mentioned will be the input as well. Classifier will then, based on the training, give marks to the
answers. Marks to the answer will be the final output.
INTRODUCTION
The manual system for evaluation of Subjective Answers for technical subjects involves a lot of time and effort of the evaluator. Evaluating subjective answers is a critical task to Perform. When a human being evaluates anything, the quality of evaluation may vary along with the emotions of the person. Performing
evaluation through computers using intelligent techniques ensures uniformity in marking as the same inference mechanism is used for all the students. In Machine Learning, all results are only based on the input data provided by the user. Our Proposed System uses machine learning and NLP to solve this problem. Our Algorithm performs a task like tokenizing words and sentences, Part of speech tagging, Chunking, chinking, lemmatizing words and Wordnetting to evaluate the subjective answer. Our system will evaluate answers based on some keywords and also manpower will be saved. Our System is divided into two modules, Extracting the data from the printed documents of answer and organizing it in the proper manner and Applying ML and NLP to the text retrieved from the above step and giving marks to them. The software will take a printed copy of the answer as an input and then after, it will extract the text of the answer. This text will again go through processing to build a model of keywords and feature sets. Model answer sets and keywords categorized as mentioned will be the input .Based on the keywords written in the answer and the keywords in the dataset the application will provide marks in the certain range. Marks to the answer will be the final output. The need for online examination is mainly to overcome the drawbacks of the existing system. The main aim of the project is to ensure user friendly and more interactive software to the user evaluation project.
The online evaluation is a much faster and clear method to define all the relevant marking schemes. It brings much transparency to the present method of answer checking the answers to all the questions after the extraction would be stored in a database. The database is designed as such that it is very easily accessible. The work of checking hundreds of answer sheets which more or less contains the same answer can be a burden task. This system can be used instead in order to reduce their burden. It will save a lot of effort and time on teachers’ part. The human efforts applied in this repetitive task can be saved and spent more in other academic endeavors.
The obvious human mistakes can be reduced to obtain an unbiased result. The system calculates the score and provides results fairly quickly. This system can be widely used in academic institutions such as schools, colleges, coaching and institutes for checking answer sheets . It can also be implemented in different organizations which conduct competitive examinations.
Decision Tree Algorithm :
Classification is a two-step process, learning step and prediction step, in machine learning. In the learning step, the model is developed based on given training data. In the prediction step, the model is used to predict the response for given data. Decision Tree is one of the easiest and popular classification algorithms to understand and interpret. The Decision Tree algorithm belongs to the family of supervised learning algorithms. Unlike other supervised learning algorithms, the decision tree algorithm can be used for solving regression and classification problems too. The goal of using a Decision Tree is to create a training model that can be used to predict the class or value of the target variable by learning simple decision rules inferred from prior data(training data). In Decision Trees, for predicting a class label for a record we start from the root of the tree. We compare the values of the root attribute with the record’s attribute. On the basis of comparison, we follow the branch corresponding to that value and jump to the next node.
Types of decision trees are based on the type of target variable we have evaluation project. It can be of two types:
Categorical Variable Decision Tree: Decision Tree which has a categorical target variable then it is called a Categorical variable decision tree.
Continuous Variable Decision Tree: Decision Tree has a continuous target variable then it is called Continuous Variable Decision Tree. Terminology related to Decision Trees
Root Node: It represents the entire population or sample and this further gets divided into two or more homogeneous sets.
Splitting: It is a process of dividing a node into two or more sub-nodes.
Decision Node: When a sub-node splits into further sub-nodes, then it is called the decision node.
Leaf / Terminal Node: Nodes that do not split are called Leaf or Terminal nodes.
Pruning: When we remove sub-nodes of a decision node, this process is called pruning. You can say the opposite process of splitting.
Branch / Sub-Tree: A subsection of the entire tree is called branch or sub-tree.
Parent and Child Node: A node, which is divided into sub-nodes is called a parent node of sub-nodes whereas sub-nodes are the child of a parent node.
The algorithm selection is also based on the type of target variables. Let us look at some algorithms used in Decision Trees:
ID3 → (extension of D3)
C4.5 → (successor of ID3)
CART → (Classification And Regression Tree)
CHAID → (Chi-square automatic interaction detection Performs multi-level
splits when computing classification trees)
MARS → (multivariate adaptive regression splines)
Advantages of Decision Trees:
● There are several advantages of using decision trees for predictive analysis:
● Decision trees can be used to predict both continuous and discrete values i.e. they work well for both regression and classification tasks.
● They require relatively less effort for training the algorithm.
● They can be used to classify non-linearly separable data.
● They’re very fast and efficient compared to KNN and other classification
algorithm
