Comparative Study on Heterogeneous Profiling Sources for Second Language Learners

Adaptive E-learning systems, which provide personalized learning experiences based on learner's specific characteristics (e.g. knowledge, skills, and competencies), are essential for developing effective learning and teaching. This paper presents a conceptual proposition consisting in developing adaptive E-learning system by incorporating egocentric network-based user profiling, an existing contribution of our research team. Actually, this contribution has been proved in the online social network context with empirical results on different social networks data (Facebook, Delicious, Twitter and DBLP). We aim to apply the existing algorithms underlying this contribution in E-learning context and present in this work a conceptual model and the construction process of learner's user profile, called profile. The learner profile can be exploited in adaptive E-learning systems to provide different personalized/adapted services (books recommendation, personalized courses search, ...) to the learner.

Selection of genes that are differentially expressed and critical to a particular biological process has been a major challenge in post-array analysis. Recent development in bioinformatics has made various data sources available such as mRNA and miRNA expression profiles, biological pathway and gene annotation, etc. Efficient and effective integration of multiple data sources helps enrich our knowledge about the involved samples and genes for selecting genes bearing significant biological relevance. In this work, we studied a novel problem of multi-source gene selection: given multiple heterogeneous data sources (or data sets), select genes from expression profiles by integrating information from various data sources. We investigated how to effectively employ information contained in multiple data sources to extract an intrinsic global geometric pattern and use it in covariance analysis for gene selection. We designed and conducted experiments to systematically compare the proposed approach with representative methods in terms of statistical and biological significance, and showed the efficacy and potential of the proposed approach with promising findings.

Entity alignment is the problem of identifying which entities in a data source refer to the same real-world entity in the others. Identifying entities across heterogeneous data sources is paramount to many research fields, such as data cleaning, data integration, information retrieval and machine learning. The aligning process is not only overwhelmingly expensive for large data sources since it involves all tuples from two or more data sources, but also need to handle heterogeneous entity attributes. In this paper, we propose an unsupervised approach, called EnAli, to match entities across two or more heterogeneous data sources. EnAli employs a generative probabilistic model to incorporate the heterogeneous entity attributes via employing exponential family, handle missing values, and also utilize the locality sensitive hashing schema to reduce the candidate tuples and speed up the aligning process. EnAli is highly accurate and efficient even without any ground-truth tuples. We illustrate the performance of EnAli on re-identifying entities from the same data source, as well as aligning entities across three real data sources. Our experimental results manifest that our proposed approach outperforms the comparable baseline.

It is challenging to identify meaningful gene networks because biological interactions are often condition-specific and confounded with external factors. It is necessary to integrate multiple sources of genomic data to facilitate network inference. For example, one can jointly model expression datasets measured from multiple tissues with molecular marker data in so-called genetical genomic studies. In this paper, we propose a joint conditional Gaussian graphical model (JCGGM) that aims for modeling biological processes based on multiple sources of data. This approach is able to integrate multiple sources of information by adopting conditional models combined with joint sparsity regularization. We apply our approach to a real dataset measuring gene expression in four tissues (kidney, liver, heart, and fat) from recombinant inbred rats. Our approach reveals that the liver tissue has the highest level of tissue-specific gene regulations among genes involved in insulin responsive facilitative sugar transporter mediated glucose transport pathway, followed by heart and fat tissues, and this finding can only be attained from our JCGGM approach.

As the exponential growth of data in internet era, the era of big data is coming. Big data integration creates huge values that makes it a research hotspot. However, in big data era, data shows characters of large volume, velocity, veracity and especially variety which is also called heterogeneity. Multiple different sources of data lead to data heterogeneity. Multi-source heterogeneous data brings challenges to big data integration. In this paper, we proposes a big data integration platform based on hybrid hierarchy architecture, which classifies the underlying multi-source heterogeneous data sources according to themes, and uses the data warehouse as the middle-tier data source. Then user uses the mediator to directly access the middle-tier data source through pattern mapping. Experiments show that compared with the traditional method of directly connecting the underlying data source, this data integration platform improves query performance.

The increasing availability of numerous heterogeneous but related sources of data arises in many fields, such as bioinformatics, robotics, computer vision, information retrieval, and many others. Multiple sources of data can be viewed as different, related views of the same learning problem, where dependencies between the views could potentially take on complex structures. This gives rise to interesting and challenging machine learning problems where data sources are combined for learning. This framework encompasses several data fusion tasks and related topics, such as transfer learning, multitask learning, multiview learning, and learning under covariate shift. Often the general concept is to augment training data for each problem of interest with data from other partially related learning problems. Several approaches for inferring and exploiting complex relationships between sources have been presented. The advantages of the multiple source learning paradigm can be seen in situations where individual data sources are noisy, incomplete, and learning from more than one source can filter out problem-independent noise. Additionally, another aspect of multiple source learning is that data sources need only contain partially relevant information to the desired learning problem, making it possible to exploit a large number of data sources. This special issue on “Learning from Multiple Sources” was inspired by a successful (eponymous) NIPS workshop which took place in Whistler (Canada) on December 13, 2008. The workshop received twenty-three submissions, from which seven contributed talks and

In recent years, huge different biological databases have been stored in various locations. Using distinct data sets from multiple sources results in more reliable data analysis. However, it is so difficult to combine heterogeneous data in one single server. The most obvious reasons include data privacy, large data sizes, costs, and different geographical locations of data sources. In this paper, we present two new algorithms for clustering data from multiple remote data sources using kernel k-means. The first algorithm is the center-based algorithm built on k-means algorithm. The second algorithm uses distributed kernel k-means over multiple data sources. In the distributed scheme, clustering methods are executed only on their local data sources themselves. Partial clustering results are synched between data sources. To evaluate performance of our proposed algorithms, we merged all data from different sources into one large data set to perform kernel k-means. The results showed that our center-based algorithm greatly reduced transmission data between data sources while still yielding acceptable clustering results. Our distributed kernel k-means algorithm achieved even better performance. The clustering results are very close to those generated by kernel k-means on one merged data set.

True mean value discovery over multiple data sources with unknown reliability degrees

Purpose The purpose of this study is to present a systematic and comprehensive review of personalized, adaptive and semantic e-learning systems. Design/methodology/approach Preferred reporting items of systematic reviews and meta-analyses guidelines have been used for a thorough insight into associated aspects of e-learning that complement the e-learning pedagogies and processes. The aspects of e-learning systems have been reviewed comprehensively such as personalization and adaptivity, e-learning and semantics, learner profiling and learner categorization, which are handy in intelligent content recommendations for learners. Findings The adoption of semantic Web based technologies would complement the learner’s performance in terms of learning outcomes. Research limitations/implications The evaluation of the proposed framework depends upon the yearly batch of learners and recording is a cumbersome/tedious process. Social implications E-Learning systems may have diverse and positive impact on society including democratized learning and inclusivity regardless of socio-economic or geographic status. Originality/value A preliminary framework of an ontology-based e-learning system has been proposed at a modular level of granularity for implementation, along with evaluation metrics followed by a future roadmap.

Relatively mature integration technologies are available that make application integration tractable from an engineering perspective. However, integrating multiple heterogeneous data sources into applications is still a time-consuming, costly and error-prone engineering task, because existing integration technologies are based on static integration architectures. Such architectures tightly couple a data source to the data integration infrastructure. This paper describes the architecture and evolving prototype implementation of the Data Concierge, which provides a dynamic solution to integrate heterogeneous data sources. The core architecture and mechanisms in the Data Concierge can be used for dynamically attaching to a previously unidentified source of information, without the need for a pre-existing adapter component. In this paper, an ontology based API description mechanism supported by the Data Concierge is described, along with the architecture and prototype tools for describing the metadata necessary to facilitate dynamic integration. The use of an ontology and associated state machine to generate API calls to access data sources is illustrated using an FTP data source.

Learning logs or reflective journals are frequently used in further and higher education to encourage students' reflection on their learning. Such approaches are rare in school. This study employed a learning log over a five-week period, with a class of 14–15 year old students learning about digestion, respiration and breathing at a Suffolk upper school in the UK. The study aimed to establish (1) how the learning log can prompt reflection on the learning benefits of classroom activities and increase cognitive control of learning strategies, and (2) how greater understanding of learning strategies may affects students' motivation to learn. The learning logs themselves formed one source of data. Student reflections on the learning benefits of classroom activities were also assessed through classroom dialogue and semi-structured interviews. Motivation was assessed at the start and at the end of the teaching sequence, using a questionnaire. The learning log did stimulate student reflection, but did not prompt the level of learning strategy awareness that emerged in the semi-structured interviews. Suggestions are made (1) for modifications to the learning log, and (2) for how the learning log can provide a mechanism for continuous student feedback on teaching and learning activities.

Research on learner profiling in education primarily focuses on utilizing students’ personal characteristics and behavioral data to depict their learning status and traits. However, existing methods often face challenges such as incomplete data and difficulties in feature extraction, leading to incomplete and less accurate learner profiles. To address information gaps in learner profiles within educational datasets, this study proposes a profile completion technique based on relation-aware heterogeneous graph networks. Using the MOOCCube and MOOCCubeX datasets, we trained a relation-aware heterogeneous graph network model to predict students’ age and gender. The model achieved significant advancements in gender prediction. While age prediction performance remains relatively low—a common challenge in the field due to the subtle and multifaceted nature of age-related behavioral signals—ablation studies confirm the model’s robustness, demonstrating stable gender prediction accuracy even with significant data reduction. This work bridges information gaps in learner profiling within educational datasets, providing crucial support for personalized education and teaching quality improvement. It showcases the potential application of relation-aware heterogeneous graph networks in education and offers new ideas for research utilizing heterogeneous graph networks for learner profiling.

In the era of big data, enterprises increasingly rely on near-real-time data ingestion pipelines to drive advanced analytics and machine learning models. The complexity and diversity of heterogeneous data sources pose significant challenges to maintaining high data quality and error resilience in these pipelines. This paper investigates strategies to ensure robust data quality and error management within autonomous self-schedulable libraries designed for handling diverse data formats. We explore architectural designs, best practices, and innovative techniques that enable seamless integration and real-time processing of disparate data sources. Key areas of focus include error detection and correction mechanisms, data validation frameworks, and resilient pipeline orchestration. Through comprehensive case studies and experimental evaluations, we demonstrate the efficacy of these strategies in enhancing the reliability and accuracy of data ingestion processes. Our findings provide a roadmap for enterprises seeking to optimize their data pipelines, ensuring they are equipped to handle the complexities of heterogeneous data environments with minimal human intervention.

Language learning is a complex process influenced by individual personality traits (Ellis, 2008). Recognizing these traits can lead to more effective and personalized educational approaches (Dörnyei & Skehan, 2003), focusing on enhancing motivation, perseverance, and learning preferences. Educators can create successful language learning experiences by considering learners' strengths and weaknesses and offering appropriate support. Language learning strategies hold significant importance among learner characteristics, as they are consistently associated with higher L2 achievement and self-regulated language learning. However, language learning strategies do not act in isolation; they interact with other learner-related variables, including personality. While some research exists on the connection between personality traits and strategic learning, it remains limited and fragmented, often relying on outdated research instruments. As teachers strive to better understand how personality influences language learning strategies, further exploration is needed to unlock valuable insights and optimize language learning experiences. To fill this gap, Jakub Przybył and Mirosław Pawlak (2023) published a book entitled “Personality as a Factor Affecting the Use of Language Learning Strategies: The Case of University Students” as an attempt to link the reported use of language learning strategies by tertiary L2 learners in Poland to their personality traits.

Many studies on language learning have highlighted the advantages of collaborative writing (CW) in promoting learners’ writing skills (Strobl, 2014). To achieve the end product of collaborative writing tasks, learners are required to work collaboratively in various stages of planning and editing the writing as well as finalizing the shared texts (Woodrich & Fan, 2017). According to Storch (2011), although CW has been widely used and found to be very effective in promoting writing learning, it has been practiced mostly outside the context of second language (L2) learning. However, Kessler et al. (2012) suggested that with the assistance of technologies, we can integrate Web 2.0[1] applications and pedagogical practices in teaching and learning writing to enhance students’ writing via online CW.