Designing and delivering web application courses for computing undergraduates is a challenging task. Lack of understanding of web concepts affects the students” interest in web application development. Therefore., faculty employ several traditional strategies including hands on exercises and labs as well as innovative strategies such as videos and discussion forums. However., due to the volume of the posts in the forums., the instructors find it challenging to attend to the students' challenges and focus on more challenging topics across the classroom. In this paper., we propose a text mining based solution to extract the questions and complex topics. We evaluated the solution on the year 2 Web Application course offered to the computing undergraduates. Our experiments show that logistic regression model performs better in classifying question posts and cosine similarity performs better in assigning the topic label to the posts. The findings are visually depicted and are useful to the faculty to identify the topics that requires more attention to improve students' learning.

As computing projects increasingly become a core component of undergraduate courses, effective mentorship is crucial for supporting students' learning and development. Our study examines the adoption of ChatGPT as a mentor for undergraduate computing projects. It explores the impact of ChatGPT mentorship, specifically, skills development, and mentor responsiveness, i.e., ChatGPT’s responsiveness to students' needs and requests. We utilize PLS-SEM to investigate the interrelationships between different factors and develop a model that captures their contribution to the effectiveness of ChatGPT as a mentor. The findings suggest that mentor responsiveness and technical/design support are key factors for the adoption of AI tools like ChatGPT. The study provides practical implications for educators seeking to incorporate AI as a mentor to support students doing computing projects and contributes to the broader understanding of the use of AI in education.

In introductory programming courses, students as novice programmers would benefit from doing frequent practices set at a difficulty level and concept suitable for their skills and knowledge. However, setting many good programming exercises for individual learners is very time-consuming for instructors. In this work, we propose an automated exercise generation system, named ExGen, which leverages recent advances in pre-trained large language models (LLMs) to automatically create customized and ready-to-use programming exercises for individual students on- demand. The system integrates seamlessly with Visual Studio Code, a popular development environment for computing students and software engineers. ExGen effectively does the following: 1) maintaining a set of seed exercises in a personalized database stored locally for each student; 2) constructing appropriate prompts from the seed exercises to be sent to a cloud-based LLM deployment for generating candidate exercises; and 3) implementing a novel combination of filtering checks to automatically select only ready-to-use exercises for a student to work on. Extensive evaluation using more than 600 Python exercises demonstrates the effectiveness of ExGen in generating customized, ready-to-use programming exercises for new computing students.

Today, computing graduates see a bright outlook thanks to the high demand for skills driven by the increasing importance of technology as the main driving force behind business transformation. As technology continues to grow exponentially over recent years, computing graduates have some of the highest starting salaries in the market [20] [19]. Even though universities have increased production of computing degree graduates in recent years, it is insufficient to fill the jobs available in the market [14]. Therefore, going forward, the demand is likely to further increase. The continued demand for computing programs in universities has led to an increased intake size, thus straining faculty workloads. Universities must consider funneling more resources into computing programs to address faculty’s increasing workload. Past studies have shown that peer learning environments enable increased productivity for faculty and enhanced educational quality for students [27] [15]. In this article, we describe a peer assisted learning model for an introductory programming course — Coders Assembly — designed and driven by undergraduate students in a computing program. Our model centers on four key areas – process, people, content, and technology. We reflect on our experience of implementing this peer assisted learning model and the result of a student survey.

With increasing data volume and adoption of technologies including machine learning and artificial intelligence across all industries, the demand for skilled Data Science professionals is continuing to increase globally. For educational institutions to teach the most up-to-date and industry-relevant skills and for businesses to hire employees with the right set of skills, it is important for them to stay tuned to the fast-changing dynamics of job landscape. In this research study, we present an NLP approach to the analysis of job listings from Glassdoor. Our solution mines insights on trending technical and soft skills in the Data Science job categories. Based on the insights, we provide recommendations to design overall data science curriculum learning outcomes (LOs). We also provide recommendations to the course designers on specific technical skills required for the topics of courses under the data science curriculum.

In this study, we showcase a design of an undergraduate Business Analytics track that integrates professional certifications from Amazon Web Services, Google, SAS, and Salesforce with core Business Analytics courses in an Information Systems undergraduate degree program. Certifications provide an excellent way for students to attain practical, experiential, and demonstrable skills which increasingly more employers look for in job candidates' portfolios. In close collaboration with industry partners, curriculum designers and faculty in institutions of higher learning can leverage high quality hands-on training materials provided by the certification vendors and align it with the core academic course content. Excellent teaching by the faculty combined with industry-relevant practical certification training is the recipe for a successful career building for Information Systems students.

This research paper presents a group project framework for a second-year programming course, which was conducted during the COVID-19 pandemic. The framework offers well defined stages of the group project which allow students to work on their choice of a real-world problem, integrate their learnings from previous courses, and present a working solution. In the group project, students actively participate, reflect, and contribute to achieving the goals set in the learning objectives of the course. Our framework incorporates key features from Kolb's Experiential Learning Theory (1984) and principles of active learning from Barnes (1989) to achieve active and experiential learning through active supervision. The use of group projects as a teaching pedagogy is widely adopted in many universities. Students work together, develop a plan, and demonstrate their abilities in building on existing knowledge acquired from previous courses, and apply them appropriately for problem solving. Prior to the pandemic, it was the norm for students to work on their group projects together by meeting physically on campus. Key benefits of working together physically are having the support of one another and the ease of communication. With the onset of the pandemic, safe distancing measures, and restrictions put in place have made it challenging for students to work on group projects together. During the pandemic, many courses were forced to move online with limited face-to-face learning opportunities on campus. This posed great challenges to the faculty in terms of effective supervision of students and their project progress. To mitigate the challenges, we devised a flexible strategy that makes use of both technology-based and non-technological means for monitoring students' group project milestones. The faculty receives continuous updates from students as they work towards each milestone. These milestones serve as important checkpoints for students. Continuous checks at different milestones help the faculty adopt appropriate intervention measures as issues arise. The group project learning framework consists of three main stages, namely Group Formation, Scoping of the Project, and Group Solutioning. The framework is overlaid with Kolb's Experiential Learning Theory concepts to describe the learnings, milestones, and deliverables of each stage. Each of these stages adopts Barnes's principles of active learning to enable active participation, reflection, and contribution by students. We evaluated the success of this framework through a comprehensive student survey analysis. The survey asked specific questions to students on all stages of the group project and the overarching component of teamwork and working online. We also present our findings and lessons learned for improvements of the framework. We believe that our framework will be valuable to educators in computing programs that wish to adopt effective supervision measures for group projects.

Having students write short self-reflections at the end of each weekly session enables them to reflect on what they have learnt in the session and topics they find challenging. Analysing these self-reflections provides instructors with insights on how to address the missing conceptions and misconceptions of the students and appropriately plan and deliver the next session. Currently, manual methods adopted to analyse these student reflections are time consuming and tedious. This paper proposes a solution model that uses content mining and NLP techniques to automate the analysis of short self-reflections. We evaluate the solution model by studying its implementation in an undergraduate Information Systems course through a comparison of three different content mining techniques namely LDA–bigrams, GSDMM-bigrams, and Word2Vec based Clustering models. The evaluation involves both qualitative and quantitative methods. The results show that the proposed techniques are useful in discovering insights from the self-reflections, though the performance varied across the three methods. We provide insights into comparisons of the perspectives, which are useful to instructors.

Constructive interactions through discussion forums allow students to open their horizons and thought processes to acquire more knowledge and develop skills. Thus, discussion forums play an important role in supporting learning. Additionally, the discussion forum provides the content for creating a knowledge repository. It contains discussion threads related to key course topics that are debated by the students. One approach to understanding the student learning experience is through the analysis of the discussion threads. This research proposes the application of discourse analysis and collaborative learning frameworks to discussion forums to gain further insights into the student's learning in a classroom. It is a foray into discourse analysis using in-class discussions. It demonstrates the application of Soller's framework and Penn Discourse Treebank (PDTB) to understand interactions at the discourse and semantic level. It also shows the use of unsupervised automated techniques to diagnose interactions in textual data. In this paper, we present an Integrated Discourse Analysis and Collaborative Learning Skills (IDALS) framework based on in-class discussions. We describe our experiences of applying IDALS framework and evaluating the solution model in a graduate in-class discussion forum. We also highlight the benefits of using visualizations to present the insights to the instructors.

This research full paper, describes knowledge management of class discussions using an analytics based framework. Discussions, either live classroom or through online forums, when used as a teaching method can help stimulate critical thinking. It allows the teacher to explore in-depth the key concepts covered in the course, motivates students to articulate their ideas clearly and challenge the students to think more deeply. Analysing the discussions helps instructors gain better insights on the personal and collaborative learning behaviour of students. However, knowledge from in-class discussions and online forums is not effectively captured and mined due to lack of appropriate automated tools. In this paper, the authors propose an automated discussion analysis (ADA) framework that provides a starting point providing guidance on the development of automated tools for performing different analysis on live classroom or online discussions. AI technology plays a key role in developing tools for knowledge representation and analysis. We propose software systems based on ADA framework and AI technology. The paper then describes a case study where one model of the ADA framework, individual behaviour analysis model, has been applied to automate the analysis of the online discussion forum used in a postgraduate course.

Our research full paper studies the perceptions of students and proposes technology design framework for smart class participation tools. Participation in classroom discussions has been observed to improve student comprehension and performance. In our contemporary tertiary educational context, student participation is characterised in mainly two forms; in-class discussions and online forums. Both forms of participation generate voluminous amounts of knowledge. However, the present difficulty in capturing and analysing these forms of participation leads to loss of knowledge and insights, which otherwise could be very useful. This study aims to analyse ways to improve data capture as well as data analysis of discussions. In this paper, we take a survey-based approach to study the students' perception of classroom discussions in terms of three components namely effective learning, technology support and grading. Based on the analysis of the survey results, we propose the design of a tool and the administrative requirements needed for in-class participation data capture and analysis. We present our results in the form of a framework for tool design and challenges to be addressed when using technology during class discussions.

Discussion forums play a key role in building knowledge repositories in an education institute. Asynchronous discussion forums enable part-time graduate professionals to have a better learning experience. This paper reports how a carefully curated discussion forum enhances the cognitive and social interactions among students in a graduate information systems course. In particular, we analyse the cognitive and social interactions and their impact on the student grades. To our surprise, the graduate students with their limited time resources, have higher order cognitive contributions and reasonable amount of social posts. We present the discussion forum design, cognitive and social behaviour analysis, grade analysis, and social network analysis. We use statistical methods and qualitative analysis to present our findings. Our findings provide useful insights that can be used in designing and implementing discussion forums in graduate business-technical courses.

This Innovative Practice full paper, describes the application of text mining techniques for extracting insights from a course based online discussion forum through generation of topic based summaries. Discussions, either in classroom or online provide opportunity for collaborative learning through exchange of ideas that leads to enhanced learning through active participation. Online discussions offer a number of benefits namely providing additional time to reflect and synthesize information before writing, providing a natural platform for students to voice their ideas without any one student dominating the conversation, and providing a record of the student's thoughts. An online discussion forum provides a repository comprising the discussion threads related to the topics discussed. One approach to extracting useful knowledge from the repository is through generation of concise summaries of the discussion for each topic. This summary information can help both the instructor and the student in being able to focus on the key learning points discussed in the forum threads. The focus of our research is directed towards analysis of online discussion forums (ODFs) and generating topic based summaries that can be viewed by both instructor and the students. We have developed a tool, Topic Based Summarization (TBS), that takes an excel sheet with discussion forum thread posts as input and generates visual reports of summaries that are clustered into different topics. We evaluate the tool using discussion thread posts for an undergraduate course titled “Business Process Modelling and Solutioning”. We also performed qualitative analysis of the tool to investigate the strengths and weakness of various summarization algorithms.

Discussion forums provide the base content for creating a knowledge repository. It contains discussion threads related to key course topics that are debated by the students. In order to better understand the student learning experience, the instructor needs to analyse these discussion threads. This paper proposes the use of clustering models and interactive visualizations to conduct a qualitative analysis of graduate discussion forums. Our goal is to identify the sub-topics and topic evolutions in the discussion forums by applying text mining techniques. Our approach generates insights into the topic analysis in the forums and discovers the students’ cognitive understanding within and beyond the classroom learning settings. We developed the analysis model and conducted our experiments on a graduate course in Information Systems. The results show that the proposed techniques are useful in discovering knowledge from the forums and generating user-friendly visualizations. Such results can be used by the faculty to analyse the students’ discussions and study the strengths and weaknesses of the students’ cognitive knowledge on course topics.

Reaching to young generation and attracting them to computing programs such as Information Systems (IS) and Computer Science (CS) is a key challenge faced by universities in Singapore. During their application process, many high quality students from junior colleges (JC) either don't choose IS program or choose IS program as the last option. School of Information Systems (SIS), Singapore Management University, decided to implement an innovative outreach program to reach and attract high quality JC students. A team of 30 faculty and staff worked on an outreach project to study and analyse the rationale behind the smaller numbers of applicants. We surveyed JC students and the results showed that only 5% of top JC students were aware of the term “Information Systems” and this seemed to be the root cause for low numbers and quality of applications to IS school. This shows that awareness is the first issue that should be tackled in our outreach. The outreach team unanimously agreed on executing an outreach camp which is designed to familiarize JC students on three main aspects; the value of IS in solving real world problems, common IS topics and IS related jobs. We have executed several outreach camps since our first run and have observed significant improvements in the number and quality of applications. In this paper, we share the gamified design of the outreach camp, results, challenges and lesson learnt in running an innovative IS outreach camp. We hope, our project will aid the university outreach teams in designing and organizing the outreach camps to the Gen-Z students.

Teacher evaluation is a vital element in improving student learning outcomes. Course and instructor feedback given by students, provides insights that can help improve student learning outcomes and teaching quality. Teaching and course evaluation systems help to collect quantitative and qualitative feedback from students. Since manually analysing the qualitative feedback is painstaking and a tedious process, usually, only the quantitative feedback is often used for evaluating the course and the instructor. However, useful knowledge is hidden in the qualitative comments, in the form of sentiments and suggestions that can provide valuable insights to help plan improvements in the course content and delivery. In order to efficiently gather, analyse and provide deeper insights from student feedback by topics, we developed a user-friendly application, Student Feedback Analysis Tool (SUFAT). The tool is an independent desktop application that can be installed and used by any nontechnical user. The tool takes an excel sheet with comments as an input and generates an excel sheet with visual reports of summaries that include sentiments and suggestions as an output. The tool can benefit instructors to quickly analyse the termly qualitative feedback and take appropriate actions. We intend to release the tool for public use so that instructors can download and install the tool on their computer system.

This Innovate Practice full paper, describes our experience in using the mini-case pedagogy to design and deliver a technical course, “Enterprise Integration” which is a year two course in the Information Systems undergraduate program. Case method is one approach that has been widely adopted in teaching many professions including law, medicine and business. The general practice is to ask students to read the case, usually four to eight pages long, prior to the session, and then spend the whole session discussing the case. However, for technology courses, the students are required to learn concepts and apply them using hands-on software tools through lab sessions. Hence, rather than use long cases, that cover the entire session, we need to use mini-cases that are usually one to two pages long. This pedagogy approach allows the class session to be designed with tight integration across the concept presentation lecture, mini-case analysis and hands-on lab session. We share the pedagogy implementation details and challenges, and discuss our findings and lessons learnt in designing and implementing the mini-case pedagogy. Thus providing one pathway for Information Systems and Computer Science professors to, implement the mini-case pedagogy in “technology heavy” courses.

Wikis are widely used collaborative environments as sources of information and knowledge. The facilitate students to engage in collaboration and share information among members and enable collaborative learning. In particular, Wikis play an important role in capstone projects. Wikis aid in various project related tasks and aid to organize information and share. Mining project Wikis is critical to understand the students learning and latest trends in industry. Mining Wikis is useful to educationists and academicians for decision-making about how to modify the educational environment to improve student's learning. The main challenge is that the content or data in project Wikis is unstructured in nature. The data formats are in both text and images. In this work, we propose an automated project Wiki mining solution that leverages data mining, text mining and optical character recognition techniques for discovering insights from Project Wikis. The results of mining process are presented as visual summaries which can be useful for the capstone project coordinators and academicians for education pedagogy decisions. We use dataset from Singapore Management University, School of Information Systems' undergraduate capstone projects for our solution evaluation. We evaluated our model on 314 capstone projects over a period of 8 years.

In academic institutions it is normal practice that at the end of each term, students are required to complete a questionnaire that is designed to gather students' perceptions of the instructor and their learning experience in the course. This questionnaire comprises of Likert-scale questions and qualitative questions. One of the important goals of this exercise is to enable the instructor and the senior management to examine the feedback and then enhance students' learning experience. In most universities, including our own, a lot of attention is paid to the quantitative feedback, which is summarized and statistical comparisons are computed, analysed and presented. However, the qualitative comments given by the students are not fully tapped. Capturing and analysing the qualitative feedback data, at the individual course, school and university-level, can provide valuable insights on teaching practices and curriculum. In this paper, we propose a conceptual framework for student feedback analysis that provides the necessary structure for implementing a prototype tool for mining student comments. We then discuss the application of the tool to analyse feedback from selected courses.

Real world information technology projects cut across multiple business domains and processes, involve large amounts of data and an assortment of different technologies. Advanced courses within an IS programs must include projects that help students gain a holistic view of an enterprise by exposing them to business domains, business processes and technical knowledge and skills that will help them design and deliver enterprise projects. In order to guide the instructor to effectively design and implement such enterprise project experiences, in this paper, we propose an enterprise integrated project environment (EIPE) framework based on business domains and business processes. Additionally, we share our experience in implementing this framework in the Data Warehousing and Business Analytics course. The analysis of the student feedback for this course demonstrates the benefits of EIPE in enhancing student learning experience. We share the project details and challenges and discuss our findings and lessons learnt in designing and implementing EIPE. Thus providing one pathway for Information Systems professors to, design an enterprise integrated project in their courses.

The overall aim of learning outcomes and competency based education is to improve the efficiency and effectiveness of higher education. It's important to track regularly student's competency acquisition so that the faculty can improve the teaching delivery and adapt the content accordingly. Student based self-assessment of competency tracking on a weekly basis aids faculty to intervene in course delivery process for effective teaching and learning experience. It also helps students to have a better understanding of their competency levels and accordingly prepare for weekly sessions. To enable students to self-assess the competencies in more structured format, there is a need for a systematic tracking tool. Additionally, it is also important for this tool to leverage on the latest technology for enhancing user friendliness and provide pervasive access through mobile technology. In this paper, we present a mobile web application, MyCompetencies, which enables faculty and students to track competencies on a weekly basis. We evaluated the tool in an undergraduate course over one semester comprising 110 students. We experiments showed that the tool helped the faculty to intervene and adapt the content to the students' learning pace.

SFIA skills framework is widely popular among education institutions and ICT industries. The framework provides ICT skills profiles which can be a valuable resource that supports the career planning of a student. However, currently a student does not have a method or approach to exploit the SFIA framework to align his or her competencies that he or she has acquired during the education program, to the skills defined in the SFIA framework. In this paper, we present a solution model for generating a skills report based on individual's competencies and experiences. In particular, we focus on Information Systems students' profiles. Student skill generator takes in curriculum and LinkedIn profile's data as an input and generates student's skills report which is aligned with SFIA framework. Moreover, the system also generates a list of recommended jobs in ICT sector that match the student's skills. We evaluated our solution model on an undergraduate core curriculum; Bachelor of Science (Information Systems Management) degree program BSc (ISM), offered by the School of Information Systems (SIS), Singapore Management University (SMU) and LinkedIn profiles of student from year 3, year 4 and alumni.

Human grading of introductory programming assignments is tedious and errorprone, hence researchers have attempted to develop tools that support automatic assessment of programming code. However, most such efforts often focus only on scoring solutions, rather than assessing whether students correctly understand the problems. To aid the students improve programming skills, effective feedback on programming assignments plays an important role. Individual feedback generation is tedious and painstaking process. We present a tool that not only automatically generates the static and dynamic program analysis outcomes, but also clusters similar code submissions to provide scalable and effective feedback to the students. We studied our tool on data from introductory Java programming assignments of year 1 course in School of Information Systems. In this paper, we share the details of our tool and findings of our experiments on 261 code submissions.

Universities collect qualitative and quantitative feedback from students upon course completion in order to improve course quality and students' learning experience. Combining program-wide and module-specific questions, universities collect feedback from students on three main aspects of a course namely, teaching style, content, and learning experience. The feedback is collected through both qualitative comments and quantitative scores. Current methods for analyzing the student course evaluations are manual and majorly focus on quantitative feedback and fall short of an in-depth exploration of qualitative feedback. In this paper, we develop student feedback mining system (SFMS) which applies text analytics and opinion mining approach to provide instructors a quantified and exhaustive analysis of the qualitative feedback from students and avail insights on their teaching practices and this in turn will lead to improved student learning.

The application of learning outcomes and competency frameworks have brought better clarity to engineering programs. Several frameworks have been proposed to integrate outcomes and competencies into course design, delivery and assessment. However, in many cases, competencies are course-specific and their overall impact on the curriculum is unknown. Such impact analysis is important for analyzing and improving the curriculum design. Unfortunately, manual analysis is a painstaking process due to large amounts of competencies across the curriculum. In this paper, we propose an automated method to discover their impact on the overall curriculum design. We provide a principled methodology for discovering the impact of courses’ competencies using Bloom’s Taxonomy and the learning outcomes framework.

A common problem in large urban cities is the huge number of retail options available. In response, a number of shopping assistance applications have been created for mobile phones. However, these applications mostly allow users to know where stores are or find promotions on specific items. What i

Most social networking platforms protect user's private information by limiting access to it to a small group of members, typically friends of the user, while allowing (virtually) everyone's access to the user's public data. In this paper, we exploit public data available on Facebook to infer users' undisclosed interests on their profile pages. In particular, we infer their undisclosed interests from the public data fetched using Graph APIs provided by Facebook. We demonstrate that simply liking a Facebook page does not corroborate that the user is interested in the page. Instead, we perform sentiment-oriented mining on various attributes of a Facebook page to determine the user's real interests. Our experiments conducted on over 34,000 public pages collected from Facebook and data from volunteers show that our inference technique can infer interests that are often hidden by users on their personal profile with moderate accuracy. We are able to disclose 22 interests of a user and find more than 80,097 users with at least 2 interests. We also show how this inferred information can be used to break a preference based backup authentication system.

Community Question Answering (CQA) websites, where people share expertise on open platforms, have become large repositories of valuable knowledge. To bring the best value out of these knowledge repositories, it is critically important for CQA services to know how to find the right experts, retrieve archived similar questions and recommend best answers to new questions. To tackle this cluster of closely related problems in a principled approach, we proposed Topic Expertise Model (TEM), a novel probabilistic generative model with GMM hybrid, to jointly model topics and expertise by integrating textual content model and link structure analysis. Based on TEM results, we proposed CQARank to measure user interests and expertise score under different topics. Leveraging the question answering history based on long-term community reviews and voting, our method could find experts with both similar topical preference and high topical expertise. Experiments carried out on Stack Overflow data, the largest CQA focused on computer programming, show that our method achieves significant improvement over existing methods on multiple metrics.

We explore Debatepedia, a communityauthored encyclopedia of sociopolitical debates, as evidence for inferring a lowdimensional, human-interpretable representation in the domain of issues and positions.We introduce a generative model positing latent topics and cross-cutting positions that gives special treatment to person mentions and opinion words.We evaluate the resulting representation's usefulness in attaching opinionated documents to arguments and its consistency with human judgments about positions.0.1 0.2 0.3 0.4 0.5 comment, minimum, wage, poverty, capitalism nuclear, weapons, iran, states, threat party, vote, republican, political, voters energy, gas, power, fuel, wind

Online software forums provide a huge amount of valuable content. Developers and users often ask questions and receive answers from such forums. The availability of a vast amount of thread discussions in forums provides ample opportunities for knowledge acquisition and summarization. For a given search query, current search engines use traditional information retrieval approach to extract webpages containing relevant keywords. However, in software forums, often there are many threads containing similar keywords where each thread could contain a lot of posts as many as 1,000 or more. Manually finding relevant answers from these long threads is a painstaking task to the users. Finding relevant answers is particularly hard in software forums as: complexities of software systems cause a huge variety of issues often expressed in similar technical jargons, and software forum users are often expert internet users who often posts answers in multiple venues creating many duplicate posts, often without satisfying answers, in the world wide web. To address this problem, this paper provides a semantic search engine framework to process software threads and recover relevant answers according to user queries. Different from standard information retrieval engine, our framework infer semantic tags of posts in the software forum threads and utilize these tags to recover relevant answer posts. In our case study, we analyze 6,068 posts from three software forums. In terms of accuracy of our inferred tags, we could achieve on average an overall precision, recall and F-measure of 67%, 71%, and 69% respectively. To empirically study the benefit of our overall framework, we also conduct a user-assisted study which shows that as compared to a standard information retrieval approach, our proposed framework could increase mean average precision from 17% to 71% in retrieving relevant answers to various queries and achieve a Normalized Discounted Cumulative Gain (nDCG) @1 score of 91.2% and nDCG@2 score of 71.6%.