Dr Hassan Khosravi

Snr Lecturer, Learning Analytics

Institute for Teaching and Learning Innovation

Affiliate Academic

School of Information Technology and Electrical Engineering
Faculty of Engineering, Architecture and Information Technology
h.khosravi@uq.edu.au
+61 7 334 60774

Overview

Research achievements and breakthroughs are critical to the growth and reputation of universities, however, the very core of any post-secondary institute is its students and facilitating their learning. Dr Hassan Khosravi strongly believes in the importance of excellent teaching and has dedicated much of his time during the last decade towards this goal.

As a computer scientist by training, Hassan is passionate about applying innovative analytic approaches from fields such as machine learning, data mining, and visualisation to rich and complex digital data available on learners with the goal of personalising education and improving outcomes for all students. He is passionate about exploiting techniques with pedagogical benefits that promote active learning and developing new technologies that intervene in real-time to support students in decision-making.

Hassan's personal experience in teaching, especially large classes, has prepared him well for research in learning analytics and higher education. His teaching career includes instructing roughly 20 different offerings, with class sizes ranging from 50 to 350, of 10 distinct courses to a total of roughly 2500 students. He has the experience and enthusiasm to teach first-year introductory programming courses to majors and non-majors, second-year data structures and software engineering courses, upper-level courses in algorithms, artificial intelligence, database management, and graduate-level courses in data science. Hassan has strived to incorporate effective techniques and innovations that promote active learning such as the use of classroom response systems (clickers), flipped classroom methodologies, peer learning systems (e.g., PeerWise), collaborative learning (e.g., two-stage exams), online discussion board (e.g., Piazza), problem-based learning, and massive open online courses into his teaching. In 2015, he was honoured with a UBC Computer Science Department Teaching Award, which is presented to a few of the more than fifty faculty members in the Department for recognition of outstanding teaching. He has also received numerous “congratulations on excellent teaching” letters from the Dean of Faculty of Science at UBC, which are presented to academics recieving an average score of higher than 4.5 for student responses to the statement ”Overall, the instructor was an effective teacher”, with 1 indicating "Strongly Disagree" and 5 indicating "Strongly Agree"

Research Interests

  • Learning Analytics, Higher Education, Machine Learning, CS Education

Qualifications

  • Doctor of Philosophy, Simon Fraser University

Publications

View all Publications

Supervision

  • Master Philosophy

  • Master Philosophy

View all Supervision

Available Projects

  • Are you interested in applying novel and innovative analytic approaches from fields such as machine learning, data mining, and visualisation to address highly challenging and world-changing tasks such as enhancing and personalising education? If yes, then please send me an email supplying a cover letter, your academic transcript with grades/GPA, and your CV. Applicants who successfully meet entry requirements for PhD and are awarded an Australian Postgraduate Award (APA) might be eligible for annual top-up scholarships.

    Also accepting Honours and part-time PhD students, as well as undergraduate students wanting voluntary research roles over the semester.

  • The aim of this project is to develop a framework that enables adoption of student-facing learning dashboards. Learning dashboards apply innovative visualisation approaches to rich and complex digital data available on students to support exploration of learning activities. Students can use the visualisations for self-reflection and a better understanding of their strengths and weaknesses. In addition, through exposure to innovative visualisation approaches, students will develop an appreciation for methods of communication and externalisation of knowledge from complex data sets. The framework will be designed to be extensible, broadly applicable, and scalable - supporting the diverse needs of the digitally minded students of the 21st century. A prototype, based on the framework, will be developed and implemented in partnership with a coordinator of a large first-year course. This prototype will be used to examine the effectiveness of the use of learning dashboards in large first-year courses.

  • UQx creates Massive Open Online Courses (MOOCs) for the EDx platform (https://www.edx.org/school/uqx) and collects student interactions with courseware and interactive activities. UQx is building open source tools to process learner clickstream data and present visualisations to course stakeholders.

    In this project, we aim to (1) design and develop new visualisations for the UQx learning analytics dashboard, and (2) develop machine learning algorithms to better understand learner’s behaviours taking online courses.

    The project deliverables include extensions to the open source UQx Dashboard project (https://github.com/UQ-UQx/dashboard_js).

View all Available Projects

Publications

Journal Article

Conference Publication

  • Khosravi, Hassan and Cooper, Kendra (2017). Using learning analytics to investigate patterns of performance and engagement in large classes. In: Proceedings of the 2017 ACM SIGCSE Technical Symposium on Computer Science Education. SIGCSE '17, Seattle, WA, United States, (309-314). 8-11 March 2017. doi:10.1145/3017680.3017711

  • Khosravi, Hassan (2013). Fast parameter learning for Markov logic networks using Bayes nets. In: Inductive Logic Programming - 22nd International Conference, ILP 2012, Revised Selected Papers. 22nd International Conference on Inductive Logic Programming, ILP 2012, Dubrovnik, Croatia, (102-115). 17-19 September 2012. doi:10.1007/978-3-642-38812-5_8

  • Khosravi, Hassan, Bozorgkhan, Ali and Schulte, Oliver (2013). Transaction-based link strength prediction in a social network. In: Proceedings of the 2013 IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013 IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013, Singapore, (191-198). 16-19 April 2013. doi:10.1109/CIDM.2013.6597236

  • Khosravi, Hassan and Bina, Bahareh (2010). A survey on statistical relational learning. In: Advances in Artificial Intelligence - 23rd Canadian Conference on Artificial Intelligence, Canadian AI 2010, Proceedings. 23rd Canadian Conference on Artificial Intelligence, Canadian AI 2010, Ottawa, ON, Canada, (256-268). 31 May - 2 June 2010. doi:10.1007/978-3-642-13059-5_25

  • Khosravi, Hassan, Schulte, Oliver, Man, Tong, Xu, Xiaoyuan and Bina, Bahareh (2010). Structure learning for Markov Logic Networks with many descriptive attributes. In: AAAI-10 / IAAI-10 - Proceedings of the 24th AAAI Conference on Artificial Intelligence and the 22nd Innovative Applications of Artificial Intelligence Conference. 24th AAAI Conference on Artificial Intelligence and the 22nd Innovative Applications of Artificial Intelligence Conference, AAAI-10 / IAAI-10, Atlanta, GA, United States, (487-493). 11-15 July 2010.

  • Schulte, Oliver, Frigo, Gustavo, Greiner, Russell and Khosravi, Hassan (2010). The IMAP hybrid method for learning Gaussian bayes nets. In: Advances in Artificial Intelligence - 23rd Canadian Conference on Artificial Intelligence, Canadian AI 2010, Proceedings. 23rd Canadian Conference on Artificial Intelligence, Canadian AI 2010, Ottawa, ON, Canada, (123-134). 31 May - 2 June 2010. doi:10.1007/978-3-642-13059-5_14

  • Schulte, Oliver, Frigo, Gustavo, Greiner, Russell, Luo, Wei and Khosravi, Hassan (2009). A new hybrid method for bayesian network learning with dependency constraints. In: Symposium on Computational Intelligence and Data Mining, 2009 CIDM '09. IEEE Symposium on. 2009 IEEE Symposium on Computational Intelligence and Data Mining (Cidm), Nashville, TN, (53-60). 30 March - 2 April 2009. doi:10.1109/CIDM.2009.4938629

  • Khosravi, Hassan and Colak, Recep (2009). Exploratory Analysis of Co-Change Graphs for Code Refactoring. In: Advances in Artificial Intelligence, Proceedings. 22nd Canadian Conference on Artificial Intelligence, Kelowna Canada, (219-223). May 25-27, 2009.

  • Bina, Bahareh, Schulte, Oliver and Khosravi, Hassan (2009). LNBC: A link-based naive bayes classifier. In: ICDM Workshops 2009 - IEEE International Conference on Data Mining. 2009 IEEE International Conference on Data Mining Workshops, ICDMW 2009, Miami, FL, (489-494). December 6, 2009-December 6, 2009. doi:10.1109/ICDMW.2009.116

  • Khosravi H., Shiri M.E., Khosravi H., Iranmanesh E. and Davoodi A. (2008). TACtic- a multi behavioral agent for trading agent competition. In: Advances in Computer Science and Engineering - 13th International CSI Computer Conference, CSICC 2008, Revised Selected Papers. 13th International Computer Society of Iran Computer Conference on Advances in Computer Science and Engineering, CSICC 2008, Kish Island, (811-815). March 9, 2008-March 11, 2008. doi:10.1007/978-3-540-89985-3_109

Other Outputs

PhD and MPhil Supervision

Current Supervision

Possible Research Projects

Note for students: The possible research projects listed on this page may not be comprehensive or up to date. Always feel free to contact the staff for more information, and also with your own research ideas.

  • Are you interested in applying novel and innovative analytic approaches from fields such as machine learning, data mining, and visualisation to address highly challenging and world-changing tasks such as enhancing and personalising education? If yes, then please send me an email supplying a cover letter, your academic transcript with grades/GPA, and your CV. Applicants who successfully meet entry requirements for PhD and are awarded an Australian Postgraduate Award (APA) might be eligible for annual top-up scholarships.

    Also accepting Honours and part-time PhD students, as well as undergraduate students wanting voluntary research roles over the semester.

  • The aim of this project is to develop a framework that enables adoption of student-facing learning dashboards. Learning dashboards apply innovative visualisation approaches to rich and complex digital data available on students to support exploration of learning activities. Students can use the visualisations for self-reflection and a better understanding of their strengths and weaknesses. In addition, through exposure to innovative visualisation approaches, students will develop an appreciation for methods of communication and externalisation of knowledge from complex data sets. The framework will be designed to be extensible, broadly applicable, and scalable - supporting the diverse needs of the digitally minded students of the 21st century. A prototype, based on the framework, will be developed and implemented in partnership with a coordinator of a large first-year course. This prototype will be used to examine the effectiveness of the use of learning dashboards in large first-year courses.

  • UQx creates Massive Open Online Courses (MOOCs) for the EDx platform (https://www.edx.org/school/uqx) and collects student interactions with courseware and interactive activities. UQx is building open source tools to process learner clickstream data and present visualisations to course stakeholders.

    In this project, we aim to (1) design and develop new visualisations for the UQx learning analytics dashboard, and (2) develop machine learning algorithms to better understand learner’s behaviours taking online courses.

    The project deliverables include extensions to the open source UQx Dashboard project (https://github.com/UQ-UQx/dashboard_js).

  • Due to the extensive number of eLearning objects (e.g., videos, articles, review questions), available to learners, it becomes more challenging for them to identify those that best suit their needs in effectively mastering the material. The primary goal of the project is to employ exemplary techniques from the fields of learning analytics and Recommender Systems for Technology Enhanced Learning (RecSysTEL) to harness the rich available data on students to provide accurate, personalised recommendations on learning objects for individual students that reflect both their knowledge gaps and preferences. To find out more about this work please see https://arxiv.org/abs/1704.00556

  • Use of videos has become a crucial aspect of both on-line and on-campus education. In addition to their direct benefit in communicating facts, demonstrating procedures, or providing personalised feedback to assist in mastery learning, use of videos allows for recording of digital traces of learners' interaction and navigation on a video, via a media player, that provide insights into student learning.

    The aim of this project is to use video analytic techniques to investigate the impact of students' use of a system called vMarks, which provides on-the-go video feedback for assessment in large courses.

  • Educators continue to face significant challenges in providing high quality, post-secondary instruction in large classes including motivating and engaging diverse populations (e.g., academic ability and backgrounds, generational expectations), and providing helpful feedback and guidance. The primary goal of this project is to apply learning analytics techniques to explore the data collected from large introductory classes to (1) identify groups of students with similar patterns of performance and engagement, and (2) provide them with more meaningful appraisals that are tailored to help them effectively master the learning objectives. Fore more information please see http://www.cs.ubc.ca/~hkhosrav/pub/SIGCSE2017.pdf