Semantic User Research Articles

Investigations of Semantic Usage and Aspect-te-iru for (sa)seru type of Verbs

Investigations of Semantic Usage and Aspect-te-iru for (sa)seru type of Verbs

Semantic audio content-based music recommendation and visualization based on user preference examples

Preference elicitation is a challenging fundamental problem when designing recommender systems. In the present work we propose a content-based technique to automatically generate a semantic representation of the user’s musical preferences directly from audio. Starting from an explicit set of music tracks provided by the user as evidence of his/her preferences, we infer high-level semantic descriptors for each track obtaining a user model. To prove the benefits of our proposal, we present two applications of our technique. In the first one, we consider three approaches to music recommendation, two of them based on a semantic music similarity measure, and one based on a semantic probabilistic model. In the second application, we address the visualization of the user’s musical preferences by creating a humanoid cartoon-like character – the Musical Avatar – automatically inferred from the semantic representation. We conducted a preliminary evaluation of the proposed technique in the context of these applications with 12 subjects. The results are promising: the recommendations were positively evaluated and close to those coming from state-of-the-art metadata-based systems, and the subjects judged the generated visualizations to capture their core preferences. Finally, we highlight the advantages of the proposed semantic user model for enhancing the user interfaces of information filtering systems.

An investigation of discourse markers in English

1 IntroductionSemantic connectives have long been a focus of research in cognitive and language development. Such connectives as so, because, and but encode causal and adversative relations among events and create textual cohesion (Halliday and Hasan, 1976). Recently, however, researchers have been examining other types of relations that need to be encoded in discourse. Deborah Schiffrin (1987), for example, has focused on 'discourse markers (DMs)', a broader category of connective or relational forms than semantic connectives. Discourse markers are linguistic, paralinguistic, or nonverbal elements that signal relations between of talk by virtue of their syntactic and semantic properties and by virtue of their sequential relations as initial or terminal brackets demarcating discourse units (Schiffrin, 1987: 40). During everyday communication, speakers use discourse markers a lot.Since the 1970s interest in DMs has increased with growing interest in the production and comprehension of extended discourse and, more generally, in pragmatic and contextual aspects of utterance interpretation. During the past ten years, the study of DMs has explored in linguistics, with dozens of articles appearing yearly. This broadening of interest brought about increased attention to those elements of linguistic structure that appear to be most directly involved in the relation of separate utterances. Within this new perspective many elements in sentence-based linguistic research have been paid more attention, including many expressions, such as well, and y'know, etc. which had previously been regarded as unworthy of close attention. Research on DMs has expanded continually throughout the 1980s and 1990s because it was found that they have prominent role, not only in pragmatic and discourse analytic research but also in studies of language acquisition and language pedagogy, and in research on sociolinguistic topics. Within the past ten years or so there has been an increasing interest in the theoretical status of DMs, focusing on what they are, what they mean, and what functions they have.The analysis of discourse markers is part of the more general analysis of discourse coherence-how speakers and hearers jointly integrate forms, meaning, and actions to make overall sense out of what is said. (Schiffrin, 1987: 49)Innovation in language affects all areas of society. A case in point is a number of discourse/pragmatic markers in the English language which have gained considerable attention in recent years, from the media, educationalists and linguists alike.1.1 Similar TerminologiesThere are different terminologies including discourse connectives (Blakemore, 1987, 1992), discourse operators (Redeker, 1990, 1991), discourse particles (Schorup, 1985), discourse signaling devices (Polanyi and Scha, 1983), phatic connectives (Bazanella, 1990), pragmatic connectives (van Dijk, 1979; Stubbs, 1983), pragmatic expressions (Erman, 1992), pragmatic formatives (Fraser, 1987), pragmatic markers (Fraser, 1988, 1990; Schiffrin, 1987), pragmatic operators (Ariel, 1994), pragmatic particles (Ostman, 1995), semantic conjuncts (Quirk et al., 1985), sentence connectives (Halliday and Hasan, 1976). (As cited in Fraster, 1999)Despite the quantity of research in this area, however, no consensus has emerged regarding fundamental issues of terminology and classification. The term DM used in this paper is the most popular of all those terms used. Brinton (1996) lists more than twenty such terms. A close second in frequency of occurrence is the term discourse particle (DP) which predominated until the mid 1980s, but in this paper discourse marker is preferable.1.2 Discourse markersMany language learners' primary goal of language learning experiences is 'grammatical' language, which is the accurate usage of syntax, phonology, morphology, and semantics. As Svartik notes, language learners may be corrected for using non-standard morphology but will not be corrected for using a discourse marker in an inappropriate place, even if the lack of that marker taints the learner's talk as somehow deficient (1980, in Muller, 2004; cf. …

A Semantic and Environment Models-Based User Behavior Prediction Scheme in Smart Home

A Semantic and Environment Models-Based User Behavior Prediction Scheme in Smart Home

연관 피드백과 퍼지 함의 연산자를 이용한 스니핏 추출 방법

In information retrieval, search engine provide the rank of web page and the summary of the web page information to user. Snippet is a summaries information of representing web pages. Visiting the web page by the user is affected by the snippet. User sometime visits the wrong page with respect to user intention when uses snippet. The snippet extraction method is difficult to accurate comprehending user intention. In order to solve above problem, this paper proposes a new snippet extraction method using fuzzy implication operator and relevance feedback. The proposed method uses relevance feedback to expand the use`s query. The method uses the fuzzy implication operator between the expanded query and the web pages to extract snippet to be well reflected semantic user`s intention. The experimental results demonstrate that the proposed method can achieve better snippet extraction performance than the other methods.

An Adaptive System Supporting Collaborative Learning Based on a Location-Based Social Network and Semantic User Modeling

This paper presents an adaptive e-learning system which supports collaborative learning based on a location-based social network and semantic modeling. In the system, a social network among e-learning learners is dynamically constructed on the basis of the location information of learners using GPS sensors for collaborative learning. In addition, user modeling for semantic social network and adaptive e-learning is supported. For these, a mechanism that supports the construction of a dynamic social network using the location information of smart phones is provided. The user modeling for the construction of a semantic social network and the support of adaptive e-learning considers the information such as the users' achievement, preference, and learning goal. Through this system, e-learners can find mentors who are able to facilitate their learning and create communities for collaborative learning offline and online. The support of a location-based social network service and semantic user model in our system would increase interactions among e-learners and improve satisfaction regarding their mobile learning environment.

Parse Mechanism of Manufacturing Information Needs Based on Workflow Context

In this paper, the definitions of workflow context and its formal description for manufacturing information based on RDF/S (Resource Description Framework/Schema) are studied. And then, the logical structure and structure storeage of the independent context space are built. On the basis above, the parse mechanism of the information needs and the search mechanism of manufacturing information are studied. The algorithms of semantic search and user requirement extraction based on workflow context are developed.

A personalized search using a semantic distance measure in a graph-based ranking model

The goal of search personalization is to tailor search results to individual users by taking into account their profiles, which include their particular interests and preferences. As these latter are multiple and change over time, personalization becomes effective when the search process takes into account the current user interest. This article presents a search personalization approach that models a semantic user profile and focuses on a personalized document ranking model based on an extended graph-based distance measure. Documents and user profiles are both represented by graphs of concepts issued from predefined web ontology, namely, the Open Directory Project directory (ODP). Personalization is then based on reordering the search results of related queries according to a graph-based document ranking model. This former is based on using a graph-based distance measure combining the minimum common supergraph and the maximum common subgraph between the document and the user profile graphs. We extend this measure in order to take into account a semantic recovery at exact and approximate concept-level matching. Experimental results show the effectiveness of our personalized graph-based ranking model compared with Yahoo and different personalized ranking models performed using classical graph-based measures or vector-space similarity measures.

The biomedical discourse relation bank

BackgroundIdentification of discourse relations, such as causal and contrastive relations, between situations mentioned in text is an important task for biomedical text-mining. A biomedical text corpus annotated with discourse relations would be very useful for developing and evaluating methods for biomedical discourse processing. However, little effort has been made to develop such an annotated resource.ResultsWe have developed the Biomedical Discourse Relation Bank (BioDRB), in which we have annotated explicit and implicit discourse relations in 24 open-access full-text biomedical articles from the GENIA corpus. Guidelines for the annotation were adapted from the Penn Discourse TreeBank (PDTB), which has discourse relations annotated over open-domain news articles. We introduced new conventions and modifications to the sense classification. We report reliable inter-annotator agreement of over 80% for all sub-tasks. Experiments for identifying the sense of explicit discourse connectives show the connective itself as a highly reliable indicator for coarse sense classification (accuracy 90.9% and F1 score 0.89). These results are comparable to results obtained with the same classifier on the PDTB data. With more refined sense classification, there is degradation in performance (accuracy 69.2% and F1 score 0.28), mainly due to sparsity in the data. The size of the corpus was found to be sufficient for identifying the sense of explicit connectives, with classifier performance stabilizing at about 1900 training instances. Finally, the classifier performs poorly when trained on PDTB and tested on BioDRB (accuracy 54.5% and F1 score 0.57).ConclusionOur work shows that discourse relations can be reliably annotated in biomedical text. Coarse sense disambiguation of explicit connectives can be done with high reliability by using just the connective as a feature, but more refined sense classification requires either richer features or more annotated data. The poor performance of a classifier trained in the open domain and tested in the biomedical domain suggests significant differences in the semantic usage of connectives across these domains, and provides robust evidence for a biomedical sublanguage for discourse and the need to develop a specialized biomedical discourse annotated corpus. The results of our cross-domain experiments are consistent with related work on identifying connectives in BioDRB.

Enablers for non-linear video distribution

In the last decade, video distribution has evolved from analog broadcast to fully digital video. Today, users have the freedom to decide what to watch and when to watch it, using Internet video services. Recommendation and profiling systems are there to assist the user in creating a personalized content sequence. One step further, the content itself is personalized and enabled for interactive playout. Linear content such as daily news is analyzed, segmented, filtered, and reassembled per viewer based on his profile, preferences, and available time. The transport is typically performed in a unicast fashion from a central server, which places a high demand on the network since it prevents reuse. In this paper we introduce the paradigm of late assembly. Personalized and interactive videos are generated based on semantic segments and user profiles which are combined on intermediate nodes near the end user. Together with deadline scheduling and caching, an efficient transport is realized. An architecture and a prototype implementation of this system are presented.

“My heart want to say something”: exploring ELL vocabulary use through e‐mail

PurposeThe purpose of this paper is to report on one high school English‐language‐learner's (ELL) breadth and depth of vocabulary as he communicated with his teacher through e‐mail across geographic boundaries for over 18 months.Design/methodology/approachThe authors began by separating 358 e‐mails into three time periods (first beginning, second middle, and third end) to calculate breadth using lexical density (type‐token ratios). Then, we sampled e‐mails based on personal and impersonal topics within these time periods and linguistically analyzed them for lexical cohesion, semantic usage, and derivational morphology. Interviews with participants before and after the analysis served as member checks.FindingsThe quantitative results showed a steady improvement in the breadth of the student's vocabulary over time. Qualitative analyses revealed four major uses of vocabulary within the context of e‐mail and the teacher‐student relationship.Practical implicationsGiven our findings, we offer educators insights into ELL strategies and vocabulary assessment, not only with e‐mail but in all written communication.Social implicationsA social writing tool like e‐mail can be useful for learning English in a safe, non‐threatening environment. Moreover, a trusting social relationship between communicators that develops over time can expedite the language learning process.Originality/valueVery few studies have looked at the strategic ways ELL students use vocabulary to learn English through e‐mailing.

Personalised video retrieval

A challenging problem in the user profiling domain is to create profiles of users of retrieval systems. This problem even exacerbates in the multimedia domain. Due to the Semantic Gap, the difference between low-level data representation of videos and the higher concepts users associate with videos, it is not trivial to understand the content of multimedia documents and to find other documents that the users might be interested in. A promising approach to ease this problem is to set multimedia documents into their semantic contexts. The semantic context can lead to a better understanding of the personal interests. Knowing the context of a video is useful for recommending users videos that match their information need. By exploiting these contexts, videos can also be linked to other, contextually related videos. From a user profiling point of view, these links can be of high value to recommend semantically related videos, hence creating a semantic-based user profile. This thesis introduces a semantic user profiling approach for news video retrieval, which exploits a generic ontology to put news stories into its context. Major challenges which inhibit the creation of such semantic user profiles are the identification of user's long-term interests and the adaptation of retrieval results based on these personal interests. Most personalisation services rely on users explicitly specifying preferences, a common approach in the text retrieval domain. By giving explicit feedback, users are forced to update their need, which can be problematic when their information need is vague. Furthermore, users tend not to provide enough feedback on which to base an adaptive retrieval algorithm. Deviating from the method of explicitly asking the user to rate the relevance of retrieval results, the use of implicit feedback techniques helps by learning user interests unobtrusively. The main advantage is that users are relieved from providing feedback. A disadvantage is that information gathered using implicit techniques is less accurate than information based on explicit feedback.

Modeling user hidden navigational behavior for Web recommendation

Web users exhibit a variety of navigational interests through clicking a sequence of Web pages. Analyses of Web usage data will lead to discovering Web user access patterns, and in turn, facilitating users to locate more preferable Web contents via collaborative recommendation techniques. In the context of Web usage mining, Latent Semantic Analysis (LSA) based on probability inference provides a promising approach to capture not only user hidden navigational patterns, but also the associations between users, pages and hidden navigational patterns. The discovered user access patterns could be used as a usage reference base for identifying the new user's access preferences and making usage-based collaborative Web recommendations. In this paper, we propose a novel usage-based Web recommendation framework, in which Latent Dirichlet Allocation (LDA) is employed to learn the underlying task space from the training Web log data and infer the task distribution for a target user via task inference. The main advantages of the adapted LDA model are its capabilities of efficiently learning the semantic usage information from the Web log data and effectively inferring the access preference of the target user even with a few Web clicks that might be unseen in the training data. In this paper, we also investigate the determination of an optimizing task number, which is another important problem commonly encountered in latent semantic analysis. Experiments conducted on a real Web log dataset show that this approach can achieve better recommendation performance in comparison to other existing techniques. And the discovered task-simplex expression can also provide a better interpretation for Web designers or users to better understand the user navigational preference.

Nipype: A Flexible, Lightweight and Extensible Neuroimaging Data Processing Framework in Python

Current neuroimaging software offer users an incredible opportunity to analyze their data in different ways, with different underlying assumptions. Several sophisticated software packages (e.g., AFNI, BrainVoyager, FSL, FreeSurfer, Nipy, R, SPM) are used to process and analyze large and often diverse (highly multi-dimensional) data. However, this heterogeneous collection of specialized applications creates several issues that hinder replicable, efficient, and optimal use of neuroimaging analysis approaches: (1) No uniform access to neuroimaging analysis software and usage information; (2) No framework for comparative algorithm development and dissemination; (3) Personnel turnover in laboratories often limits methodological continuity and training new personnel takes time; (4) Neuroimaging software packages do not address computational efficiency; and (5) Methods sections in journal articles are inadequate for reproducing results. To address these issues, we present Nipype (Neuroimaging in Python: Pipelines and Interfaces; http://nipy.org/nipype), an open-source, community-developed, software package, and scriptable library. Nipype solves the issues by providing Interfaces to existing neuroimaging software with uniform usage semantics and by facilitating interaction between these packages using Workflows. Nipype provides an environment that encourages interactive exploration of algorithms, eases the design of Workflows within and between packages, allows rapid comparative development of algorithms and reduces the learning curve necessary to use different packages. Nipype supports both local and remote execution on multi-core machines and clusters, without additional scripting. Nipype is Berkeley Software Distribution licensed, allowing anyone unrestricted usage. An open, community-driven development philosophy allows the software to quickly adapt and address the varied needs of the evolving neuroimaging community, especially in the context of increasing demand for reproducible research.

Personalised video retrieval

A challenging problem in the user profiling domain is to create profiles of users of retrieval systems. This problem even exacerbates in the multimedia domain. Due to the Semantic Gap, the difference between lowlevel data representation of videos and the higher concepts users associate with videos, it is not trivial to understand the content of multimedia documents and to find other documents that the users might be interested in. A promising approach to ease this problem is to set multimedia documents into their semantic contexts. The semantic context can lead to a better understanding of the personal interests. Knowing the context of a video is useful for recommending users videos that match their information need. By exploiting these contexts, videos can also be linked to other, contextually related videos. From a user profiling point of view, these links can be of high value to recommend semantically related videos, hence creating a semantic-based user profile. This thesis introduces a semantic user profiling approach for news video retrieval, which exploits a generic ontology to put news stories into its context.

Interoperable semantic access control for highly dynamic coalitions

AbstractA coalition consists of independent organizations that share resources and skills to achieve significant mission objectives. Dynamic Coalition (DC) formations occur in response to some market demands, business requests, or disaster responses, to name a few. Partners forming a coalition are automatically selected given some business criteria and become active participants from the time the coalition is formed. Highly dynamic coalitions (HDCs) form a sub class of dynamic coalitions where the coalition formation and operation are strictly bound by time in order to provide a prompt reaction to some events. This type of dynamism poses the necessity of underlying security models and technologies allowing for automated coalition formation and operation. This paper presents a platform‐driven approach to HDCs. It first defines a life cycle inherent to HDC formations, and then presents a platform‐driven access control model that takes advantage of semantics of partners' requirements to provide interoperable access control to resources shared in a coalition. Coalition partners can achieve a high level of service interoperation by enhancing their access control requirements with semantics of usage, and interlinking their semantics using class relations based on standard ontology. Copyright © 2009 John Wiley & Sons, Ltd.

Bilingualism Models: Do They Strengthen or Weaken the Oral Communicative Process in Contexts of English as a Foreign Language in Fifth Grade Primary Students?

This project presents a common and mistaken use of language that a group of fifth graders at a private bilingual school in Bogota (Colombia) experienced at class time. In a common English as a foreign language (EFL) classroom situation which encompasses models of bilingualism that may be considered “difficulties,” the author proposes some strategies to improve the communicative oral process in English, avoiding code switching and code mixing in their speech. The present research is part of a proposal on class time reading and oral activities and its applicability is up to date due to the fact that it is based on current research-tested language strategies. I conclude that code switching and code mixing may be correlated to the student’s deficiency in target language competence, but I also conclude that if the activities focus on the three aspects of accuracy, rate, and prosody, students can experience an improvement in their communicative oral process. Likewise, it was observed that the use of the native language in the form of code switching can be accepted for the clarification of a message, but only in specific circumstances (as long as teachers do not let students use the language inappropriately). The present research is offered to scholarly communities to perhaps be organized into a workshop which may make language users aware of how to improve the linguistic, syntactic, and semantic usages of a second language.

A Hybrid Recommender System Guided by Semantic User Profiles for Search in the E-learning Domain

Various concepts, methods, and technical architectures of recommender systems have been integrated into E-commerce storefronts, such as Amazon.com, Netflix, etc. Thereby, recently, Web users have become more familiar with the notion of recommendations. Nevertheless, little work has been done to integrate recommender systems into scientific information retrieval repositories, such as libraries, content management systems, online learning platforms, etc. This paper presents an implementation of a hybrid recommender system to personal the user's experience on a real online learning repository and vertical search engine named HyperManyMedia. This repository contains educational content of courses, lectures, multimedia resources, etc. The main objective of this paper is to illustrate the methods, concepts, and architecture that we used to integrate a hybrid recommender system into the HyperManyMedia repository. This recommender system is driven by two types of recommendations: content-based (domain ontology model) and rule-based (learner's interest- based and cluster-based). Finally, combining the content- based and the rule-based models provides the user with hybrid recommendations that influence the ranking of the retrieved documents with different weights. Our experiments were carried out on the HyperManyMedia semantic search engine at Western Kentucky University. We used Top-n-Recall and Top-n-Precision to measure the effectiveness of re-ranking based on the learner's semantic profile. Overall, the results demonstrate the effectiveness of the re-ranking based on personalization.

Extracting multilayered Communities of Interest from semantic user profiles: Application to group modeling and hybrid recommendations

A Community of Interest is a specific type of Community of Practice. It is formed by a group of individuals who share a common interest or passion. These people exchange ideas and thoughts about the given passion. However, they are often not aware of their membership to the community, and they may know or care little about each other outside of this clique. This paper describes a proposal to automatically identify Communities of Interest from the tastes and preferences expressed by users in personal ontology-based profiles. The proposed strategy clusters those semantic profile components shared by the users, and according to the clusters found, several layers of interest networks are built. The social relations of these networks might then be used for different purposes. Specifically, we outline here how they can be used to model group profiles and make semantic content-based collaborative recommendations.

A Stochastic Approach to Image Retrieval Using Relevance Feedback and Particle Swarm Optimization

Understanding the subjective meaning of a visual query, by converting it into numerical parameters that can be extracted and compared by a computer, is the paramount challenge in the field of intelligent image retrieval, also referred to as the ?semantic gap? problem. In this paper, an innovative approach is proposed that combines a relevance feedback (RF) approach with an evolutionary stochastic algorithm, called particle swarm optimizer (PSO), as a way to grasp user's semantics through optimized iterative learning. The retrieval uses human interaction to achieve a twofold goal: 1) to guide the swarm particles in the exploration of the solution space towards the cluster of relevant images; 2) to dynamically modify the feature space by appropriately weighting the descriptive features according to the users' perception of relevance. Extensive simulations showed that the proposed technique outperforms traditional deterministic RF approaches of the same class, thanks to its stochastic nature, which allows a better exploration of complex, nonlinear, and highly-dimensional solution spaces.