Relatedness between user input and an ideal response is a salient feature required for proper functioning of an Intelligent Tutoring System (ITS) using natural language processing. Improper assessment of text input causes maladaptation in ITSs. Meta-assessment of user responses in ITSs can improve instruction efficacy and user satisfaction. Therefore, this paper evaluates the quality of semantic matching between user input and the expected response in AutoTutor, an ITS which holds a conversation with the user in natural language. AutoTutor's dialogue is driven by the AutoTutor Conversation Engine (ACE), which uses a combination of Latent Semantic Analysis (LSA) and Regular Expressions (RegEx) to assess user input. We assessed ACE via responses from 219 Amazon Mechanical Turk users, who answered 118 electronics questions broken into 5202 response pairings (n = 5202). These analyses explore the relationship between RegEx and LSA, agreement between the two judges, and agreement between human judges and ACE. Additionally, we calculated precision and recall. As expected, regular expressions and LSA had a moderate, positive relationship, and the agreement between ACE and human was fair, but slightly lower than agreement between human.

ElectronixTutor is a new Intelligent Tutoring System for electronics that integrates multiple intelligent learning resources, including AutoTutor, Dragoon, LearnForm, ASSISTments, and BEETLE-II, as well as Point & Query hotspots on diagrams and numerous text documents on the subject of electronics. ElectronixTutor's student model contains a set of electronics knowledge components (e.g., "transistor behavior"), each of which are taught by multiple learning resources. ElectronixTutor also features a recommender system, which suggests topics and resources for the student to try based on the student model. ElectronixTutor uses a Moodle interface, and is accessible to anyone via a web browser. Currently, ElectronixTutor is being tested by undergraduate electronics students before supplementing Naval Apprentice Technician Training coursework in the fall of 2018.

Connections established between learners via interactions are seen as fundamental for connectivist pedagogy. Connections can also be viewed as learning outcomes, i.e. learners' social capital accumulated through distributed learning environments. We applied linear mixed effects modeling to investigate whether the social capital accumulation interpreted through learners' centrality to course interaction networks, is influenced by the language learners use to express and communicate in two connectivist MOOCs. Interactions were distributed across the three social media, namely Twitter, blog and Facebook. Results showed that learners in a cMOOC connect easier with the individuals who use a more informal, narrative style, but still maintain a deeper cohesive structure to their communication.

We present an overview of the design of a conversational intelligent tutoring system, called DeepTutor, based on the framework of Learning Progressions. Learning Progressions capture students' successful paths towards mastery. The assumption of the proposed tutor is that by guiding instruction based on Learning Progressions, the system will be more effective (and efficient for that matter).

The present study investigated unimodal and multimodal emotion perception by humans, with an eye for applying the findings towards automated affect detection. The focus was on assessing the reliability by which untrained human observers could detect naturalistic expressions of non-basic affective states (boredom, engagement/flow, confusion, frustration, and neutral) from previously recorded videos of learners interacting with a computer tutor. The experiment manipulated three modalities to produce seven conditions: face, speech, context, face+speech, face+context, speech+context, face+speech+context. Agreement between two observers (OO) and between an observer and a learner (LO) were computed and analyzed with mixed-effects logistic regression models. The results indicated that agreement was generally low (kappas ranged from .030 to .183), but, with one exception, was greater than chance. Comparisons of overall agreement (across affective states) between the unimodal and multimodal conditions supported redundancy effects between modalities, but there were superadditive, additive, redundant, and inhibitory effects when affective states were individually considered. There was both convergence and divergence of patterns in the OO and LO data sets; however, LO models yielded lower agreement but higher multimodal effects compared to OO models. Implications of the findings for automated affect detection are discussed.

We present AutoTutor and Affective AutoTutor as examples of innovative 21 st century interactive intelligent systems that promote learning and engagement. AutoTutor is an intelligent tutoring system that helps students compose explanations of difficult concepts in Newtonian physics and enhances computer literacy and critical thinking by interacting with them in natural language with adaptive dialog moves similar to those of human tutors. AutoTutor constructs a cognitive model of students' knowledge levels by analyzing the text of their typed or spoken responses to its questions. The model is used to dynamically tailor the interaction toward individual students' zones of proximal development. Affective AutoTutor takes the individualized instruction and human-like interactivity to a new level by automatically detecting and responding to students' emotional states in addition to their cognitive states. Over 20 controlled experiments comparing AutoTutor with ecological and experimental controls such reading a textbook have consistently yielded learning improvements of approximately one letter grade after brief 30--60-minute interactions. Furthermore, Affective AutoTutor shows even more dramatic improvements in learning than the original AutoTutor system, particularly for struggling students with low domain knowledge. In addition to providing a detailed description of the implementation and evaluation of AutoTutor and Affective AutoTutor, we also discuss new and exciting technologies motivated by AutoTutor such as AutoTutor-Lite, Operation ARIES, GuruTutor, DeepTutor, MetaTutor, and AutoMentor. We conclude this article with our vision for future work on interactive and engaging intelligent tutoring systems.

Oral discourse is the primary form of human–human communication, hence, computer interfaces that communicate via unstructured spoken dialogues will presumably provide a more efficient, meaningful, and naturalistic interaction experience. Within the context of learning environments, there are theoretical positions supporting a speech facilitation hypothesis that predicts that spoken tutorial dialogues will increase learning more than typed dialogues. We evaluated this hypothesis in an experiment where 24 participants learned computer literacy via a spoken and a typed conversation with AutoTutor, an intelligent tutoring system with conversational dialogues. The results indicated that (a) enhanced content coverage was achieved in the spoken condition; (b) learning gains for both modalities were on par and greater than a no-instruction control; (c) although speech recognition errors were unrelated to learning gains, they were linked to participants' evaluations of the tutor; (d) participants adjusted their conversational styles when speaking compared to typing; (e) semantic and statistical natural language understanding approaches to comprehending learners' responses were more resilient to speech recognition errors than syntactic and symbolic-based approaches; and (f) simulated speech recognition errors had differential impacts on the fidelity of different semantic algorithms. We discuss the impact of our findings on the speech facilitation hypothesis and on human–computer interfaces that support spoken dialogues.

We report preliminary data of an initial laboratory study examining the effectiveness of self-regulated learning (SRL) training versus no training on learners' ability to deploy SRL processes and learn about the circulatory system with MetaTutor. MetaTutor is an intelligent tutoring system (ITS) designed to train and foster learners' SRL processes while learning about several complex human body systems. We used a mixed methodology approach and include the results of a subset of the participants (N=30) whose product and process data we have analyzed. Overall, the results indicate that the SRL training group significantly outperformed the control group.

We explored the possibility of predicting learners' affective states (boredom, flow/engagement, confusion, and frustration) by monitoring variations in the cohesiveness of tutorial dialogues during interactions with AutoTutor, an intelligent tutoring system with conversational dialogues. Multiple measures of cohesion (e.g., pronouns, connectives, semantic overlap, causal cohesion, coreference) were automatically computed using the Coh-Metrix facility for analyzing discourse and language characteristics of text. Cohesion measures in multiple regression models predicted the proportional occurrence of each affective state, yielding medium to large effect sizes. The incidence of negations, pronoun referential cohesion, causal cohesion, and co-reference cohesion were the most diagnostic predictors of the affective states. We discuss the generalizability of our findings to other domains and tutoring systems, as well as the possibility of constructing real-time, cohesion-based affect detectors.

Researchers of educational technologies are often asked to do the impossible: make students learn and have them enjoy it. These two objectives, though not mutually exclusive, are frequently at odds with each other. Effective learning strategies require active knowledge use on the part of the student. Meanwhile, students typically seek to learn through the path of least effort. This can cause conflict during system interaction, and it is often the case that attitudes toward the learning environment suffer. The current study indicates that students' prior expectations of what technology can (or cannot) do may actually have a greater impact than their initial level of motivation, previous domain knowledge, and familiarity with technology, combined. Knowing these prior expectations may be a crucial step to help researchers perform the impossible.

We present in this paper an approach to assessing student paraphrases in the intelligent tutoring system iSTART. The approach is based on measuring the semantic similarity between a student paraphrase and a reference text, called the textbase. The semantic similarity is estimated using knowledge-based word relatedness measures. The relatedness measures rely on knowledge encoded in Word-Net, a lexical database of English. We also experiment with weighting words based on their importance. The word importance information was derived from an analysis of word distributions in 2,225,726 documents from Wikipedia. Performance is reported for 12 different models which resulted from combining 3 different relatedness measures, 2 word sense disambiguation methods, and 2 word-weighting schemes. Furthermore, comparisons are made to other approaches such as Latent Semantic Analysis and the Entailer.

In this paper we explored the relationship between learning gains and affective displays of an animated pedagogical agent. Students read information on the topic of computer literacy while receiving either positive or negative affective responses from an on-screen animated agent. Analyses revealed that only students with low prior knowledge were influenced by the emotion displayed by the animated agent. We discuss the generalizability of our findings to other domains and the implications of these results on intelligent tutoring systems that are emotionally intelligent.

In this paper we explored the relationship between metacognitive statements and learning gains with students' typed and spoken interactions with an intelligent tutoring system, called AutoTutor. Analyses revealed that students who entered their contributions via speech showed a significantly higher proportion of metacognitive statements (e.g., I'm not following, I understand). There was a significant negative correlation between metacognitive statements and posttest scores on both typed and spoken interactions. Students with low prior knowledge expressed more metacognitive statements than did students with high prior knowledge. Therefore, metacognitive expressions reflect the learners' knowledge deficits as opposed to improved knowledge monitoring from greater subject matter knowledge.

ARIES (Acquiring Research Investigative and Evaluative Skills) is a computerized educational game in which players attempt to stop extraterrestrials from implicitly stunting scientific progress on Earth by publishing bad research in a variety of fields. Players progress through three modules: 1) read and be tested on an on-line science text, 2) evaluate potentially flawed research articles, and 3) learn question-asking skills. ARIES incorporates multiple learning principles, such as testing effects, generation effects, and formative feedback.

The domain of artificial intelligence (AI) progresses with extraordinary vicissitude. Whereas prior authors have divided AI into the two categories of analysis and synthesis, Raine and op den Akker distinguish between four types of AI: that of appearance, function, simulation and interpretation. These subdomains of AI are differentiated by user goals, creator methodologies, and environmental constraints. In this paper, we focus on how analysis and synthesis could improve the subdomain of Functional-AI.

This paper evaluates four of the most commonly used, freely available, state-of-the-art parsers on a standard benchmark as well as with respect to a set of data relevant for measuring text cohesion, as one example of a learning technology application that requires fast and accurate syntactic parsing. We outline advantages and disadvantages of existing technologies and make recommendations. Our performance report uses traditional measures based on a gold standard as well as novel dimensions for parsing evaluation. To our knowledge, this is the first attempt to evaluate parsers across genres and grade levels for the implementation in learning technology using both gold standard and directed evaluation methods.

In this paper we study a graph-based approach to the task of textual entailment between a text and hypothesis. The approach takes into account the full lexico-syntactic context of both the text and hypothesis and relies heavily on the concept of subsumption. It starts with mapping the text and hypothesis into graph structures where nodes represent concepts and edges represent lexico-syntactic relations among concepts. Based on a subsumption score between the text-graph and hypothesis-graph an entailment decision is then made. The impact of synonymy on entailment is quantified and discussed. An important advantage of our solution is the ability to customize it so that high-confidence results are obtained.

Talking heads were integrated with two learning systems. In AutoTutor, students learn about computer literacy by holding a conversation with a student. AutoTutor is an animated pedagogical agent that asks deep reasoning questions and engages in a mixed initiative dialog as answers emerge. Students type in information via keyboard whereas AutoTutor delivers discourse sensitive contributions with facial expressions, synthesized speech, and gestures. In the Human Use Regulator Affairs (HURA) Advisor, high ranking officers in the military learn about the ethical use of human subjects on a Web site with a conversational navigational agent.

A computational prototype of negotiation behavior is presented where the following occurs: (1) agents employ different concession matching tactics; (2) agents are unaware of opponent preferences; (3) agents incur a cost for delaying settlements; (4) agents vary in terms of goal difficulty and initial offer magnitude; and (5) demands and counter-offers are made and evaluated based on the opponent's degree of concession matching. This research explores the impact of the interaction of different agent behaviors on the negotiation process and the outcome of the negotiation. Simulation experiments show that the prototype is able to manifest fundamental patterns and confirms the effectiveness of classical negotiation and mediation strategies, such as ambitious goals and aggressive concession matching tactics. The model reveals some counterintuitive patterns that may shed a new perspective on the effects of time constraints and information availability.