Get in touch with us. We'd love to hear from you.
Automating STEM Content Development
In our increasingly complex, global world, Science, Technology, Engineering and Math (STEM) learning is critical, as these disciplines help young people learn key problem-solving, team-building and creative thinking skills. Today, most countries have educational standards that include STEM curriculum. For example, in the United States, STEM figures prominently in Common Core standards, which are followed by public schools in most states. Successful STEM education relies on students solving STEM problems tied to the grade-level learning objectives specified in the Common Core standards or other national curricula. So, how are STEM problems developed?
Today, STEM problem development is a fully manual effort. Educators must find content that fits their teaching style and pedagogy, which requires substantial time, effort and, potentially, cost. Additionally, uneven problem quality, insufficient problem quantity and an inability to scale all limit the potential of STEM education. It seems only fitting that we can leverage a key STEM concept, artificial intelligence (AI), to improve STEM problem development and address these challenges.
BENEFITS & EXAMPLES OF AUTOMATION
An automated, AI approach to STEM problem development offers several key benefits. Once an AI-based platform is trained to generate STEM problems, it will create high-quality content more quickly, in greater quantity and at lower cost. Educators and students will also benefit from greater options for self-paced learning and adaptive learning pathways. Furthermore, educators can be more creative in their teaching rather than focusing on the more mundane, repetitive task of creating problem sets. The net result will be better STEM learning outcomes for more students.
Automated STEM problem development can yield a rich, comprehensive problem set. Here are five categories of STEM problems that are ideal for automation:
- New problems based on supplied parameters, including the learning objective, difficulty and desired Bloom’s Taxonomy objective. Bloom’s Taxonomy characterizes higher learning in six stages ranging from “Knowledge” of previously learned information through “Evaluation” and “Synthesis”. Example: Generate problems about “subtraction of expressions with rational exponents” that are of “medium” difficulty and that test the student’s “Comprehension” as defined by Bloom.
- Textbook tagging belonging to specific elements of Common Core or other educational standards. Today, tagging is a completely manual process. Automated tagging would identify existing problems in textbooks or other source materials and tie them to a learning objective and Bloom’s Taxonomy classification. Once identified, the tagged content would provide a model for generating sets of similar problems. Example: The tagging engine encounters the problem “Find 45% of 120.” It then analyzes the problem and identifies the learning objective as “Compute Basic Percentages.” This tagged problem becomes a model for generating similar problems.
- A set of numerical problems for specified learning objectives, difficulty and Bloom’s Taxonomy objective, based on a model. Example: Take a model problem such as “find 30% of 400” and create a set of variations.
- Problem variations with the same learning objective but on different topic. Example: For a slope calculation learning objective, an initial problem on “Construction” topic might read: “A roof rises 8.75 ft in a horizontal distance of 15.09 ft. Find the slope of the roof to the nearest hundredth.” Using automation, take the same learning objective and tailor it to “Science and Medicine” topic: “An airplane covered 15 mi of its route while decreasing its altitude by 24,000 ft. Find the slope of the line of descent.”
- Step-by-step problems and solutions. Begin with a problem specification that requires multiple steps with intermediate results to reach its solution. Using automation, deconstruct the initial problem into its sub-steps and test for a satisfactory solution of each sub-step. In addition, provide additional problems for sub-steps that are not solved correctly.
Example: Solve the quadratic equation x2-2x-8 = 0.
1. Factor the equation into two terms (x+2) and (x-4)
2. Re-state the equation as (x+2) * (x-4) = 0
3. Find the zero of each term
In these examples, automation could focus on textbooks from recognized content providers or on public-domain material. In the latter case, automation would create textbook-agnostic problem sets. Over time, we could also create a universal taxonomy that would cover the learning objectives of the major textbook publishers.
HOW AI CAN BE USED IN THE FUTURE
While AI approaches – such as natural language processing (NLP), supervised learning or machine learning – have been around for decades, the progress of hardware development has created high-performance computing nodes, which are necessary for successful AI. Through supervised learning, expert practitioners can use repeated training to improve the algorithms that classify and develop STEM problem sets. With NLP, the terms and semantic concepts of STEM problems reside in an ontology base. When building new problem sets, the appropriate ontology is automatically selected from those already in the database, creating meaningful text within the problems.
Furthermore, AI has evolved into a community-driven initiative with significant sharing and innovation through open source AI software. Software development integrates off-the-shelf tools, such as Tensorflow, Scikit-learn, NumPy, SciPy, and NLTK. Python is used to work with libraries and machine learning algorithms are implemented with C++ for improve server-side performance.
With these advances in AI, educational companies can leverage automation to develop high-quality content more quickly, in greater quantity and at a lower cost by working with a technology partner with expertise in both educational content development and AI technologies. Through this collaboration, ongoing development and thorough testing, we can improve STEM learning so students are equipped with the knowledge they need to enter the future workforce.