Addictive links, Keynote talk at WWW 2014 workshop

Click here to load reader

  • date post

  • Category


  • view

  • download


Embed Size (px)


Empirical studies of adaptive annotation in the educational context have demonstrated that it can help students to acquire knowledge faster, improve learning outcomes, reduce navigational overhead, and encourage non-sequential navigation. Over the last 8 years we have explored a lesser known effect of adaptive annotation – its ability to significantly increase student engagement in working with non-mandatory educational content. In the presence of adaptive link annotation, students tend to access significantly more learning content; they stay with it longer, return to it more often and explore a wider variety of learning resources. This talk will present an overview of our exploration of the addictive links effect in many course-long studies, which we ran in several domains (C, SQL and Java programming), for several types of learning content (quizzes, problems, interactive examples). The first part of the talk will review our exploration of a more traditional knowledge-based personalization approach and the second part will focus on more recent studies of social navigation and open social student modeling

Transcript of Addictive links, Keynote talk at WWW 2014 workshop

  • Addictive Links: Engaging Students through Adaptive Navigation Support and Open Social Student Modeling Peter Brusilovsky with: Sergey Sosnovsky, Michael Yudelson, Sharon Hsiao School of Information Sciences, University of Pittsburgh
  • MOOC Massive Open Online Course
  • Completion Rate
  • MOOC Completion Rate Classic loop user modeling - adaptation in adaptive systems
  • What Else These Students Need? Top colleges Stanford, CalTech, Princeton, GATech, Penn, Duke.. Great faculty top guns in their fields Great content Top online platform Coursera FREE!
  • The Problem of Engagement Great free content and top teachers is not enough to engage students Peter Norvig: Motivation and Engagement are key problems for MOOCs The problem is not new A lot of great advanced content Works perfectly in lab studies, great gains Released to students to enhance learning No impact students do not use it
  • The Case of QuizPACK QuizPACK: Quizzes for Parameterized Assessment of C Knowledge Each question is a pattern of a simple C program. When it is delivered to a student the special parameter is dynamically instantiated by a random value within the pre- assigned borders. Used mostly as a self- assessment tool in two C- programming courses
  • QuizPACK: Value and Problems Good news: activity with QuizPACK significantly correlated with student performance in classroom quizzes Knowledge gain rose from 1.94 to 5.37 But: Low success rate - below 40% The system is under-used (used less than it deserves) Less than 10 sessions at average Average Course Coverage below 40%
  • Adding Motivation Students need some better motivation to work with non- mandatory educational content Added classroom quizzes: Five randomly initialized questions out of 20-30 questions assigned each week Good results - activity, percentage of active questions, course coverage - all increased 2-3 times! But still not as much as we want. Could we do better? Maybe students bump into wrong questions? Too easy? Too complicated? Discouraging Lets try something that worked in the past adaptive hypermedia that can guide students to the right content
  • User Model Collects information about individual user Provides adaptation effect Adaptive System User Modeling side Adaptation side User-Adaptive Systems Classic loop user modeling - adaptation in adaptive systems
  • Adaptive Link Annotation: InterBook 1. Concept role 2. Current concept state 3. Current section state 4. Linked sections state 4 3 2 1 " Metadata-based mechanism
  • The Value of ANS Lower navigation overhead Access the content at the right time Find relevant information faster Better learning outcomes Achieve the same level of knowledge faster Better results with fixed time Encourages non-sequential navigation
  • Questions of the current quiz, served by QuizPACK List of annotated links to all quizzes available for a student in the current course Refresh and help icons QuizGuide = QuizPACK+ANS
  • Topic-Based Adaptation Concept A Concept B Concept C n Each topic is associated with a number of educational activities to learn about this topic n Each activity classified under 1 topic
  • QuizGuide: Adaptive Annotations Target-arrow abstraction: Number of arrows level of knowledge for the specific topic (from 0 to 3). Individual, event-based adaptation. Color Intensity learning goal (current, prerequisite for current, not-relevant, not-ready). Group, time- based adaptation. n Topicquiz organization:
  • QuizGuide: Success Rate nIt works! nOne-way ANOVA shows that mean success value for QuizGuide is significantly larger then the one for QuizPACK: F(1, 43) = 5.07 (p-value = 0.03).
  • QuizGuide: Motivation Adaptive navigation support increased student's activity and persistence of using the system Average activity 0 50 100 150 200 250 300 2002 2003 2004 Average num. of sessions 0 5 10 15 20 2002 2003 2004 Average course coverage 0% 10% 20% 30% 40% 50% 60% 2002 2003 2004 Active students 0% 20% 40% 60% 80% 100% 2002 2003 2004 n Within the same class QuizGuide session were much longer than QuizPACK sessions: 24 vs. 14 question attempts at average. n Average Knowledge Gain for the class rose from 5.1 to 6.5
  • A new value of ANS? The scale of the effect is too large May be just a good luck? New effect after 15 years of research? Maybe the effect could only be discovered in full-scale classroom studies while past studies were lab- based?
  • Round 2: Lets Try it Again Another study with the same system QuizGuide+QuizPACK vs. QuizPACK A study with another system using similar kinds of adaptive navigation support NavEx+WebEx vs. WebEx NavEx - a value-added ANS front-end for WebEx - interactive example exploration system
  • WebEx - Code Examples
  • Concept-based student modeling Example 2 Example M Example 1 Problem 1 Problem 2 Problem K Concept 1 Concept 2 Concept 3 Concept 4 Concept 5 Concept N Examples Problems Concepts
  • NavEx = WebEx + ANS
  • Does it work? The increase of the amount of work for the course Clicks - Overall 0 50 100 150 200 250 300 Non-adaptive Adaptive Examples Quizzes Lectures - Overall 0 2 4 6 8 10 12 Non-adaptive Adaptive Examples Quizzes Learning Objects - Overall 0 5 10 15 20 25 30 Non-adaptive Adaptive Examples Quizzes
  • Is It Really Addictive? Are they coming more often? Mostly, but there is no stable effect But when they come, they stay like with an addictive game Clicks - Per Session 0 5 10 15 20 Non-adaptive Adaptive Examples Quizzes Learning Objects - Per Session 0 1 2 3 4 Non-adaptive Adaptive Examples Quizzes
  • Why It Is Working? Progress-based annotation Displays the progress achieved so far Does it work as a reward mechanism? Open Student Modeling State-based annotation Not useful, ready, not ready Access activities in the right time Appropriate difficulty, keep motivation
  • A Deeper Look
  • The Diversity of Work C-Ratio: Measures the breadth of exploration Goal distance: Measures the depth Self-motivated Work - C-Ratio (%) 0 0.2 0.4 0.6 Non-adaptive Adaptive Quizzes Examples Self-motivated Work - Goal Distance (LO's) 0 5 10 15 20 Non-adaptive Adaptive Quizzes Examples
  • Round 3: Trying another domain Is it something relevant to C programming or to simple kind of content? New changes: SQL Programming instead of C Programming problems (code writing) instead of questions (code evaluation) Comparison of concept-based and topic-based mechanisms in the same domain and with the same kind of content
  • SQL-KnoT delivers online SQL problems, checks students answers and provides a corrective feedback Every problem is dynamically generated using a template and a set of databases All problems have been assigned to 1 of the course topics and indexed with concepts from the SQL ontology SQL Knowledge Tester
  • To investigate possible influence of concept-based adaptation in the present of topic-based adaptation we developed two versions of QuizGuide: Topic-based Topic-based+Concept-Based Concept-based vs Topic-based ANS
  • Two Database Courses (Fall 2007): Undergraduate (36 students) Graduate (38 students) Each course divided into two groups: Topic-based navigation Topic-based + Concept-Based Navigation All students had access to the same set of SQL- KnoT problems available in adaptive (QuizGuide) and in non-adaptive mode (Portal) Study Design
  • Total number of attempts made by all students: in adaptive mode (4081), in non-adaptive mode (1218) Students in general were much more willing to access the adaptive version of the system, explored more content with it and to stayed with it longer: Questions 0 25 50 75 100 Quizzes 0 5 10 15 20 25 Topics 0 1 2 3 4 5 6 Sessions 0 1 2 3 4 5 Session Length 0 5 10 15 20 25 Adaptive Non-adaptive It works again! Like magic
  • Round 4: The Issue of Complexity Lets now try it for Java What is the research goal? Java is a more sophisticated domain than C OOP versus Procedural Higher complexity Will it work for complex questions? Will it work similarly? 0% 20% 40% 60% 80% 100% C Java language complexity Easy Moderate Hard
  • Meet QuizJET!
  • Naviga&on Area Presenta&on Area JavaGuide
  • !! !! JavaGuide (Fall 2008) QuizJET (Spring 2008) !! parameters (n=22) (n=31) Overall User Statistics Attempts 125.50 41.71 Success Rate 58.31% 42.63% Distinct Topics 11.77 4.94 Distinct Questions 46.18 17.23 Average User Session Statistics Attempts 30.34 21.50 Distinct Topics 2.85 2.55 Distinct Questions 11.16 8.88 Magic Here We Go Again!
  • Round 5: Social Navigation Concept-based and topic-based navigation support work well to increase success and motivation Knowledge-based approaches require some knowledge engineering concept/topic models, prerequisites, time schedule In our past work we learned that social navigation guidance extracted from the work of a community of learners might replace knowledge-based guidance Social wisdom vs. knowledge engineering
  • Open Social Student Modeling Key ideas Assume simple topic-based design No prerequsites or concept modeling Show topic- and content- level knowledge progress of a student in contrast to the same progress of the class Main challenge How to design the interface to show student and class progress over topics? We went through several attempts
  • Parallel Introspective Views 40
  • 0 40 80 120 160 QuizJET+IV QuizJET+Portal JavaGuide Attempts Attempts Results: Progress
  • F(1,32)= 11.303, p