Sanjay k. Dwivedi

Work place: Babasaheb Bhimrao Ambedkar University, Lucknow, 226025, India



Research Interests: Information Retrieval, Data Mining, Information Systems, Multimedia Information System, World Wide Web


Prof. Sanjay K. Dwivedi is working as Professor, Department of Computer Science at Babasaheb Bhimrao Ambedkar Central University, Lucknow, India. His research interest includes Artificial
Intelligence, Information Retrieval, Web Mining, NLP and WSD. He has published a number of research papers in reputed journals and conferences. He is approachable at

Author Articles
A Reengineering based Framework for Integration of e-Governance Portal of Various State

By Ganesh Chandra Sachin Sahu Sanjay k. Dwivedi

DOI:, Pub. Date: 8 Aug. 2022

One of the most important purposes of e-Governance is to increase the satisfaction level of citizens. A single window system often helps in great way to access various government services. However, many e-Governance portals lack in integration and interoperability. Often individual state/local governments use their own portal for providing various e- services to its citizens which at times require integration and coordination with similar portals of other states for the information sharing. Lack of this feature restricts the usages of services. The realization towards this came from our previous case studies of two such portals (namely SPST and Jansunwai) of the state of Uttar Pradesh to understand the issues therein. This paper presents a general framework and guidelines for e-Governance which may be considered for implementation to overcome the existing limitations identified during the period of this study and research. The roadmap shown can improve the services, scope and functionality of certain portals. Central to this skeleton is the interconnection and integration of similar e-services being offered by different government in the country.

[...] Read more.
Selecting Appropriate Metrics for Evaluation of Recommender Systems

By Bhupesh Rawat Sanjay k. Dwivedi

DOI:, Pub. Date: 8 Jan. 2019

The abundance of information on the web makes it difficult for users to find items that meet their information need effectively. To deal with this issue, a large number of recommender systems based on different recommender approaches were developed which have been used successfully in a wide variety of domains such as e-commerce, e-learning, e-resources, and e-government among others. Moreover, in order for a recommender system to generate good quality of recommendations, it is essential for a researcher to find the most suitable evaluation metric which best matches a given recommender algorithm and a recommender's task. However, with the availability of several recommender tasks, recommender algorithms, and evaluation metrics, it is often difficult for a researcher to find their best combination. This paper aims to discuss various evaluation metrics in order to help researchers to select the most appropriate metric which matches a given task and an algorithm so as to provide good quality of recommendations.

[...] Read more.
Ambiguity in Question Paper Translation

By Shweta Vikram Sanjay k. Dwivedi

DOI:, Pub. Date: 8 Jan. 2018

Word sense ambiguity is a prevalent nature of machine translation for various language pairs including English-Hindi language. For example, the word "paper" has several senses which may refer to a question paper, research paper, newspaper, simple paper or a white paper. The specific sense intended is determined by the context in which an instance of the ambiguous word appears. This specific sense which is determined by the context is known as Word Sense Disambiguation (WSD). Translation of question paper is a specific application of MT wherein any type of ambiguity in question may affect the overall meaning of questions. This paper discusses types of ambiguity in the context of question paper translation (English to Hindi) and their impact on translation by analyzing a set of questions taken from National Council of Educational Research and Training (NCERT) and some other resources.

[...] Read more.
Keyphrase Extraction of News Web Pages

By Chandrakala Arya Sanjay k. Dwivedi

DOI:, Pub. Date: 8 Jan. 2018

Keyphrase extraction from news web pages is an important task for news documents retrieval and summarization. Keyphrases are like index terms that enclose the important information about document content. Keyphrases actually offer concise and precise description of document content. Key phrases are considered as a single word or a combination of more than one word that represent the important concepts in a text documents. The aim of this paper is to develop and evaluate an automatic keyphrases extraction approach for news web pages. Our approach identifies the candidate keyphrases from documents and chooses those candidate keyphrase having highest weight score. Weight formula combines the feature set that includes TF*IDF, phrase disatnce in documents and lexical chain that is based on WordNet to represent semantic relations between words. The experimental results show that the performance of our approach is better than the contemporary approaches today.

[...] Read more.
An Architecture for Recommendation of Courses in E-learning System

By Bhupesh Rawat Sanjay k. Dwivedi

DOI:, Pub. Date: 8 Apr. 2017

Over the last few years, the face of traditional learning has changed significantly, due to the emergence of the web. Consequently several learning systems have emerged such as computer-based learning, web-based learning among others, meeting different kinds of educational needs of the learners and educators as well. E-learning systems allow educators, distribute information, create content material, prepare assignments, engage in discussions, and manage distance classes among others. They accumulate a huge amount of data as a result of learner’s interaction with the site. This data can be used to find students’ learning pattern based on which appropriate courses could be recommended to them. However existing approaches of recommending courses to learner offer the same course to all the learners irrespective of their knowledge and skill level which results in decreasing their academic performance. This paper proposes an architecture for the recommendation of courses to a learner based on his/her profile. The profile of a learner is created by applying k-means algorithm to learner’s interaction data in moodle. The results show that the non active learners should not be recommended advanced courses if they have obtained poor marks and are not active in the concern course.  In the initial stage we discover learners’ performance in data mining course which will further be extended to other courses as well.

[...] Read more.
Assessing Query Translation Quality Using Back Translation in Hindi-English CLIR

By Ganesh Chandra Sanjay k. Dwivedi

DOI:, Pub. Date: 8 Mar. 2017

Cross-Language Information Retrieval (CLIR) is a most demanding research area of Information Retrieval (IR) which deals with retrieval of documents different from query language. In CLIR, translation is an important activity for retrieving relevant results. Its goal is to translate query or document from one language into another language. The correct translation of the query is an essential task of CLIR because incorrect translation may affect the relevancy of retrieved results.
The purpose of this paper is to compute the accuracy of query translation using the back translation for a Hindi-English CLIR system. For experimental analysis, we used FIRE- 2011 dataset to select Hindi queries. Our analysis shows that back translation can be effective in improving the accuracy of query translation of the three translators used for analysis (i.e. Google, Microsoft and Babylon). Google is found best for the purpose.

[...] Read more.
Two Way Question Classification in Higher Education Domain

By Vaishali Singh Sanjay k. Dwivedi

DOI:, Pub. Date: 8 Sep. 2015

Question classification plays vital role in Question Answering (QA) systems. The task of classifying a question to appropriate class is performed to predict the question type of the natural language question. In this paper, initially we have presented a brief overview of classification approaches adapted by different question answering systems so far and then propose a two-way question classification approach for higher education domain which not only identifies focus word and question class but also reduces answer search space within corpus comprise of question-answer pair, adding to the classification accuracy. For precise semantic interpretation of domain keywords, a domain specific dictionary is constructed which primarily have four domain word type. Classified features are built upon domain attributes in the form of constraints. The experiment proved the efficiency for restricted domain, even though we used quite simplistic approach.

[...] Read more.
Ontology based Knowledge Management for Administrative Processes of University

By Anand Kumar Sanjay k. Dwivedi

DOI:, Pub. Date: 8 Jul. 2015

Knowledge management is a challenging task especially in administrative processes with a typical workflow such as higher educational institutions and Universities. We have proposed a system aSPOCMS (An Agent-based Semantic Web for Paperless Office Content Management System) that aims at providing paperless environment for the typical workflows of the universities, which requires ontology based knowledge management to manage the files and documents of various departments and sections of a university.
In Semantic Web, Ontology describes the concepts, relationships among the concepts and properties within their domain. It provides automatic inferring and interoperability between applications which is an appropriate vision for knowledge management. In this paper we discussed, how Semantic Web technology can be utilized in higher educational institution for knowledge representation of various resources and handling the task of administrative processes. This requires exploitation of knowledge of various resources such as department, school, section, file and employee etc. of the University by aSPOCMS which is built as an agent-based system using the ontology for communication between agent, user and for knowledge representation and management.

[...] Read more.
Other Articles