Learner's Queries Research Articles

Mapping Learner's Query to Learning Objects using Topic Modeling and Machine Learning Techniques

Inquiry-based learning supports the independent knowledge development of the learner in an e-learning environment. It is crucial for the learner to obtain the appropriate Learning Object (LO) for the intended query. Mapping a learner's query to the right LO is a challenging task, as keyword-based searching on the topics or content does not guarantee the best result for various reasons. A query that apparently connects a topic may also implicitly refer to multiple other topics. Besides, the content of an LO with the same topic name often varies over different portals. Therefore, there is always a need for a method to automatically identify the latent topics of the query and then find the most relevant LO that covers the query. This paper aims to build a recommender system that maps a given input query to a suitable LO based on the most appropriate matching of learning contents. The proposed work employs an amalgamation of different supervised and unsupervised methods of natural language processing and machine learning. The machine learning model is trained on a handcrafted dataset to map queries into predefined topics. The proposed algorithm also leverages a dynamic topic modeling technique on learning content collected from three popular e-learning portals and uses a similarity score to map the learner's (user) query to the most appropriate LO.

What are language learners looking for in a collocation consultation system? Identifying collocation look-up patterns with user query data

AbstractCorpus consultation with concordancers has been recognized as a promising way for learners to study and explore language features such as collocations at their own pace and in their own time. This study examined 1.5 million search queries sent to a collocation consultation tool called FlaxCLS (Flexible Language Acquisition Collocation Learning System; http://flax.nzdl.org) over a period of two years to identify learners’ collocation look-up patterns. This paper examines and characterizes learners’ look-up patterns as they entered search queries, clicked on the query formation aids provided by the system, and navigated through the different levels of collocation information returned by the system to support collocation learning. We looked at how learners formulated query terms, and we analyzed the characteristics of query words learners entered, the characteristics of collocations they preferred, and the sample sentences they checked. Our collocation look-up pattern analyses, similar to traditional user query analyses of the web, provide interesting and revealing insights that are hard to obtain from small-scale user studies. The findings provide valuable information and pedagogical implications for data-driven learning (DDL) researchers and language teachers in designing tailored collocation consultation systems and activities. This paper also presents multidimensional analyses of learner query data, which, to the best of our knowledge, have not been explored in DDL research.

Doc2Vec based Question and Answer Search System

E-learning interaction acts as a positive factor, such as improving learning commitment and learning effect and reducing the dropout rate. As an important function of e-learning interaction, if a learner queries a content that is difficult to understand during learning, a question-and-answer bulletin board that responds to the question is provided by a professor. In the way that the instructor directly answers the learner's questions, real-time feedback is difficult, and the instructor's fatigue increases. The purpose of this study is to achieve the goal of reducing answering time and reducing answering costs by developing a question-and-answer search system that automatically searches for and provides answers to questions created by learners during learning. To this end, this study designed and implemented a question-and-answer search system that provides the most similar query answers to learners by analyzing questions and answers based on Doc2Vec, one of the word embedding technologies, which is a natural language processing technology. By applying the results of this study to the question-and-answer system, it is expected that the learning effect can be enhanced by providing an immediate answer to the learner's question. In addition, organizations that pay response fees through the national budget, such as the Korea Educational Broadcasting Corporation, will be able to focus more on investments such as improving content quality through budget reduction.

Recommendation-Based Meta-Search Engine for Suggesting Relevant Documents Links

The information available online is mostly present in an unstructured form and search engines are indispensable tools especially in higher education organizations for obtaining information from the Internet. Various search engines were developed to help learners to retrieve the information but unfortunately, most of the information retrieved is not relevant. The main objective of this research is to provide relevant document links to the learners using a three-layered meta-search architecture. The first layer retrieves information links from the web based on the learner query, which is then fed to the second layer where filtering and clustering of document links are done based on semantics. The third layer, with the help of a reasoner, categorizes information into relevant and irrelevant information links in the repository. The experimental study was conducted on a training data set using web queries related to the domain of sports, entertainment, and academics. The results indicate that the proposed meta-search engine performs well as compared to another stand-alone search engine with better recall.

Learner Initiatives in the EFL Classroom: a Public/Private Phenomenon

Abstract This paper examines how a teacher responds to ‘learner initiatives’ during classroom instruction. Learner initiatives refer to students making ‘uninvited’ contributions in class when not selected as the next speaker. This paper focuses on learners initiating an interactional sequence through asking the teacher a question. Using conversation analysis, this research describes two practices adopted by a teacher when responding to such learner initiatives. These practices shape how learners participate within learner-initiated interactional sequences and hence the opportunities that occur for learning the target language. The teacher utilizes recipient design to either better understand learner queries or explicitly answer learner questions as part of dealing with learner initiatives. This paper contributes to understanding of how learner initiatives are managed by teachers and has a role to play in teacher education by raising practitioner awareness of how this aspect of classroom interaction can be managed to further learner participation.

Virtual Standardized Patient Simulation: Case Development and Pilot Application to High-Value Care.

High-value care (HVC) suggests that good history taking and physical examination should lead to risk stratification that drives the use or withholding of diagnostic testing. This study describes the development of a series of virtual standardized patient (VSP) cases and provides preliminary evidence that supports their ability to provide experiential learning in HVC. This pilot study used VSPs, or natural language processing-based patient avatars, within the USC Standard Patient platform. Faculty consensus was used to develop the cases, including the optimal diagnostic testing strategies, treatment options, and scored content areas. First-year resident physician learners experienced two 90-minute didactic sessions before completing the cases in a computer laboratory, using typed text to interview the avatar for history taking, then completing physical examination, differential diagnosis, diagnostic testing, and treatment modules for each case. Learners chose a primary and 2 alternative "possible" diagnoses from a list of 6 to 7 choices, diagnostic testing options from an extensive list, and treatments from a brief list ranging from 6 to 9 choices. For the history-taking module, both faculty and the platform scored the learners, and faculty assessed the appropriateness of avatar responses. Four randomly selected learner-avatar interview transcripts for each case were double rated by faculty for interrater reliability calculations. Intraclass correlations were calculated for interrater reliability, and Spearman ρ was used to determine the correlation between the platform and faculty ranking of learners' history-taking scores. Eight VSP cases were experienced by 14 learners. Investigators reviewed 112 transcripts (4646 learner query-avatar responses). Interrater reliability means were 0.87 for learner query scoring and 0.83 for avatar response. Mean learner success for history taking was scored by the faculty at 57% and by the platform at 51% (ρ correlation of learner rankings = 0.80, P = 0.02). The mean avatar appropriate response rate was 85.6% for all cases. Learners chose the correct diagnosis within their 3 choices 82% of the time, ordered a median (interquartile range) of 2 (2) unnecessary tests and completed 56% of optimal treatments. Our avatar appropriate response rate was similar to past work using similar platforms. The simulations give detailed insights into the thoroughness of learner history taking and testing choices and with further refinement should support learning in HVC.

An E-Learning Recommender That Helps Learners Find the Right Materials

Learning materials are increasingly available on the Web making them an excellent source of information for building e-Learning recommendation systems. However, learners often have difficulty finding the right materials to support their learning goals because they lack sufficient domain knowledge to craft effective queries that convey what they wish to learn. The unfamiliar vocabulary often used by domain experts creates a semantic gap between learners and experts, and also makes it difficult to map a learner's query to relevant learning materials. We build an e-Learning recommender system that uses background knowledge extracted from a collection of teaching materials and encyclopedia sources to support the refinement of learners' queries. Our approach allows us to bridge the gap between learners and teaching experts. We evaluate our method using a collection of realistic learner queries and a dataset of Machine Learning and Data Mining documents. Evaluation results show our method to outperform benchmark approaches and demonstrates its effectiveness in assisting learners to find the right materials.

Improving e‐learning recommendation by using background knowledge

AbstractThere is currently a large amount of e‐Learning resources available to learners on the Web. However, learners often have difficulty finding and retrieving relevant materials to support their learning goals because they lack the domain knowledge to craft effective queries that convey what they wish to learn. In addition, the unfamiliar vocabulary often used by domain experts makes it difficult to map a learner's query to a relevant learning material. We address these challenges by introducing an innovative method that automatically builds background knowledge for a learning domain. In creating our method, we exploit a structured collection of teaching materials as a guide for identifying the important domain concepts. We enrich the identified concepts with discovered text from an encyclopedia, thereby increasing the richness of our acquired knowledge. We employ the developed background knowledge for influencing the representation and retrieval of learning resources to improve e‐Learning recommendation. The effectiveness of our method is evaluated using a collection of Machine Learning and Data Mining papers. Our method outperforms the benchmark, demonstrating the advantage of using background knowledge for improving the representation and recommendation of e‐Learning materials.

An approach for externalization of expert tacit knowledge using a query management system in an e-learning environment

<p>E-learning or electronic learning platforms facilitate delivery of the knowledge spectrum to the learning community through information and communication technologies. The transfer of knowledge takes place from experts to learners, and externalization of the knowledge transfer is significant. In the e-learning environment, the learners seek subject expertise to clarify their subject queries, and a learner query can be routed to an expert for externalization of expert knowledge provided the learner knows the subject expert or the expertise group. However, learners new to e-learning systems are not aware of the expertise group to which the query should be sent, which results in time delays, non-response, inaccurate solutions and loss of knowledge capture. Several models have been proposed to resolve this task, but thus far, these efforts have focused completely on returning the most conversant people as experts on a particular topic to retrieve valuable knowledge. To address this problem, we propose an approach that externalizes the tacit knowledge of a subject expert by creating a dynamic query handling system that automatically transfers a user query to the best subject expert.</p>

Maximum Spanning Tree Model on Personalized Web Based Collaborative Learning in Web 3.0

Web 3.0 is an evolving extension of the current web environme bnt. Information in web 3.0 can be collaborated and communicated when queried. Web 3.0 architecture provides an excellent learning experience to the students. Web 3.0 is 3D, media centric and semantic. Web based learning has been on high in recent days. Web 3.0 has intelligent agents as tutors to collect and disseminate the answers to the queries by the students. Completely Interactive learner's query determine the customization of the intelligent tutor. This paper analyses the Web 3.0 learning environment attributes. A Maximum spanning tree model for the personalized web based collaborative learning is designed.

Maximum Spanning Tree Model on Personalized Web Based Collaborative Learning in Web 3.0

Web 3.0 is an evolving extension of the current web environme bnt. Information in web 3.0 can be collaborated and communicated when queried. Web 3.0 architecture provides an excellent learning experience to the students. Web 3.0 is 3D, media centric and semantic. Web based learning has been on high in recent days. Web 3.0 has intelligent agents as tutors to collect and disseminate the answers to the queries by the students. Completely Interactive learner's query determine the customization of the intelligent tutor. This paper analyses the Web 3.0 learning environment attributes. A Maximum spanning tree model for the personalized web based collaborative learning is designed.

An Agent based Personalized Intelligent elearning

is foundation of any modern society. Self Discovery is a key to an individual's education success. Self Discovery learning is the ability of an individual to learn through personal experience and natural exploration. Online Discovery learning tends to be learner-driven and learner-initiated. Digital reposito- ry on web is supportive for online discovery learning. In recent era, availability of infrastructure, flexibility of time, learning resources and their means of sharing has increased adaptability of World Wide Web to learn and attain knowledge to a great extent. However, most of the e-learners find difficulty to select location specific, relevant and significant tutorial on the web. Search engines results pages are not based on the interest, know- ledge level and literacy rate of learner. More amount of time spent on searching and filtering and comparatively less time is devoted in actual learning. This paper proposes an agent based personalized intelligent e-learning model. The essence of perso- nalized search engine is to save learner's time to re-rank future result list. This Model uses multiple agents which delivers per- sonalized SERP (Search Engine Results Page) and is more suited for personalization of web pages based on learner's query expanded to manifold queries with novel concept of keyword research and discover knowledge using browser's behaviour. The proposed model uses web usage mining techniques to dis- cover the knowledge of learner.

Sample Complexity of Model-Based Search

We consider the problem of searching a domain for points that have a desired property, in the special case where the objective function that determines the properties of points is unknown and must be learned during search. We give a parallel to PAC learning theory that is appropriate for reasoning about the sample complexity of this problem. The learner queries the true objective function at selected points, and uses this information to choose models of the objective function from a given hypothesis class that is known to contain a correct model. These models are used to focus the search on more promising areas of the domain. The goal is to find a point with the desired property in a small number of queries. We define an analog to VC dimension, needle dimension, to be the size of the largest sample in which any single point could have the desired property without the other points' values revealing this information. We give an upper bound on sample complexity that is linear in needle dimension for a natural type of search protocol and a linear lower bound for a class of constrained problems. We also describe the relationship between needle dimension and VC dimension, explore connections between model-based search and active concept learning (including several novel positive results in active learning), and consider a scale-sensitive version of needle dimension. Several simple examples illustrate the dependence of needle dimension on features of search problems.