Search results
1 – 10 of 36Bilal Hawashin, Shadi Alzubi, Tarek Kanan and Ayman Mansour
This paper aims to propose a new efficient semantic recommender method for Arabic content.
Abstract
Purpose
This paper aims to propose a new efficient semantic recommender method for Arabic content.
Design/methodology/approach
Three semantic similarities were proposed to be integrated with the recommender system to improve its ability to recommend based on the semantic aspect. The proposed similarities are CHI-based semantic similarity, singular value decomposition (SVD)-based semantic similarity and Arabic WordNet-based semantic similarity. These similarities were compared with the existing similarities used by recommender systems from the literature.
Findings
Experiments show that the proposed semantic method using CHI-based similarity and using SVD-based similarity are more efficient than the existing methods on Arabic text in term of accuracy and execution time.
Originality/value
Although many previous works proposed recommender system methods for English text, very few works concentrated on Arabic Text. The field of Arabic Recommender Systems is largely understudied in the literature. Aside from this, there is a vital need to consider the semantic relationships behind user preferences to improve the accuracy of the recommendations. The contributions of this work are the following. First, as many recommender methods were proposed for English text and have never been tested on Arabic text, this work compares the performance of these widely used methods on Arabic text. Second, it proposes a novel semantic recommender method for Arabic text. As this method uses semantic similarity, three novel base semantic similarities were proposed and evaluated. Third, this work would direct the attention to more studies in this understudied topic in the literature.
Details
Keywords
Louisa Ha, Mohammad Hatim Abuljadail, Claire Youngnyo Joa and Kisun Kim
This study aims to examine the difference between personalized and non-personalized recommendations in influencing YouTube users’ video choices. In addition, whether men and women…
Abstract
Purpose
This study aims to examine the difference between personalized and non-personalized recommendations in influencing YouTube users’ video choices. In addition, whether men and women have a significant difference in using recommendations was compared and the predictors of recommendation video use frequency were explored.
Design/methodology/approach
A survey of 524 Saudi Arabia college students was conducted using computer-assisted self-administered interviews to collect their video recommendation sources and how likely they follow the recommendation from different sources.
Findings
Video links posted on social media used by the digital natives were found as the most effective form of recommendation shows that social approval is important in influencing trials. Recommendations can succeed in both personalized and non-personalized ways. Personalized recommendations as in YouTube recommended videos are almost the same as friends and family’s non-personalized posting of video links on social media in convincing people to watch the videos. Contrary to expectations, Saudi men college students are more likely to use recommendations than women students.
Research limitations/implications
The use of a non-probability sample is a major limitation and self-reported frequency may result in over- or under-estimation of video use.
Practical implications
Marketers will realize that they may not need the personalized recommendation from the large site. They can use social media recommendations by the consumers’ friends and family. E-mail is the worst platform for a recommendation.
Social implications
Recommendation is a credible source and can overcome the avoidance of advertising. Its influence on consumers will be increasing in years to come with the algorithmic recommendation and social media use.
Originality/value
This is the first study to compare the influence of different online recommendation sources and compare personalized and non-personalized recommendations. As recommendation is growing more and more important with algorithm development online, the study results have high reference values to marketers in Islamic countries and beyond.
Details
Keywords
The main objective of the present study is to explore whether there are variations in the employment of evaluative language resources by male and female writers. More…
Abstract
Purpose
The main objective of the present study is to explore whether there are variations in the employment of evaluative language resources by male and female writers. More specifically, the study focuses on variations, if any, that can be attributed to difference in gender.
Design/methodology/approach
The study compared and contrasted forty recommendation letters written by male academics to the same number of letters written by female recommenders. The study uses both quantitative and qualitative approaches.
Findings
The investigation of three attitudinal resources in letters of recommendations showed that the most employed resource was the judgment sub-system. The appreciation domain was in the second position, and the least frequent was the affect. The results also revealed no statistically significant variations in attitude sub-systems: Affect and appreciation as the writers in both groups (males and females) employed almost the same options in each. In respect with judgment, however, the analysis explored significant differences between the two sets as male academics used more judgment resources than females.
Originality/value
The main contributions of this study may be as follows: first, it is one of very few studies drawing on the attitude-category of appraisal system, as an analytical tool to examine gender differences in recommendation letters very particularly on the ones written by non-native speakers of English. Second, the gender factor is central in the genre of the recommendation letters and hence researchers should be cognizant of its role as certain variations might be impacted by it. Third, the lists of tokens can be offered as heuristics for academics to have most common words or phrases to use in their letters. Finally, the findings can hopefully bear some important pedagogical implications, very specifically for novice and non-native academic writers of recommendations letters.
Details
Keywords
Manjula Wijewickrema, Vivien Petras and Naomal Dias
The purpose of this paper is to develop a journal recommender system, which compares the content similarities between a manuscript and the existing journal articles in two subject…
Abstract
Purpose
The purpose of this paper is to develop a journal recommender system, which compares the content similarities between a manuscript and the existing journal articles in two subject corpora (covering the social sciences and medicine). The study examines the appropriateness of three text similarity measures and the impact of numerous aspects of corpus documents on system performance.
Design/methodology/approach
Implemented three similarity measures one at a time on a journal recommender system with two separate journal corpora. Two distinct samples of test abstracts were classified and evaluated based on the normalized discounted cumulative gain.
Findings
The BM25 similarity measure outperforms both the cosine and unigram language similarity measures overall. The unigram language measure shows the lowest performance. The performance results are significantly different between each pair of similarity measures, while the BM25 and cosine similarity measures are moderately correlated. The cosine similarity achieves better performance for subjects with higher density of technical vocabulary and shorter corpus documents. Moreover, increasing the number of corpus journals in the domain of social sciences achieved better performance for cosine similarity and BM25.
Originality/value
This is the first work related to comparing the suitability of a number of string-based similarity measures with distinct corpora for journal recommender systems.
Details
Keywords
Ulrich Herb, Eva Kranz, Tobias Leidinger and Björn Mittelsdorf
Usually the impact of research and researchers is quantified by using citation data: either by journal‐centered citation data as in the case of the journal impact factor (JIF) or…
Abstract
Purpose
Usually the impact of research and researchers is quantified by using citation data: either by journal‐centered citation data as in the case of the journal impact factor (JIF) or by author‐centered citation data as in the case of the Hirsch‐ or h‐index. This paper aims to discuss a range of impact measures, especially usage‐based metrics, and to report the results of two surveys.
Design/methodology/approach
The first part of the article analyzes both citation‐based and usage‐based metrics. The second part is based on the findings of the surveys: one in the form of a brainstorming session with information professionals and scientists at the OAI6 conference in Geneva, the second in the form of expert interviews, mainly with scientists.
Findings
The results of the surveys indicate an interest in the social aspects of science, like visualizations of social graphs both for persons and their publications. Furthermore, usage data are considered an appropriate measure to describe quality and coverage of scientific documents; admittedly, the consistence of usage information among repositories has to be kept in mind. The scientists who took part in the survey also asked for community services, assuming these might help to identify relevant scientific information more easily. Some of the other topics of interest were personalization or easy submission procedures.
Originality/value
This paper delineates current discussions about citation‐based and usage‐based metrics. Based on the results of the surveys, it depicts which functionalities could enhance repositories, what features are required by scientists and information professionals, and whether usage‐based services are considered valuable. These results also outline some elements of future repository research.
Details
Keywords
Arghya Ray, Pradip Kumar Bala and Rashmi Jain
Social media channels provide an avenue for expressing views about different services/products. However, unlike merchandise/company websites (where users can post both reviews and…
Abstract
Purpose
Social media channels provide an avenue for expressing views about different services/products. However, unlike merchandise/company websites (where users can post both reviews and ratings), it is not possible to understand user's ratings for a particular service-related comment on social media unless explicitly mentioned. Predicting ratings can be beneficial for service providers and prospective customers. Additionally, predicting ratings from a user-generated content can help in developing vast data sets for recommender systems utilizing recent data. The aim of this study is to predict ratings more accurately and enhance the performance of sentiment-based predictors by combining it with the emotional content of textual data.
Design/methodology/approach
This study had utilized a combination of sentiment and emotion scores to predict the ratings of Twitter posts (3,509 tweets) in three different contexts, namely, online food delivery (OFD) services, online travel agencies (OTAs) and online learning (e-learning). A total of 29,551 reviews were utilized for training and testing purposes.
Findings
Results of this study indicate accuracies of 58.34%, 57.84% and 100% in cases of e-learning, OTA and OFD services, respectively. The combination of sentiment and emotion scores showed an increase in accuracies of 19.41%, 27.83% and 40.20% in cases of e-learning, OFD and OTA services, respectively.
Practical implications
Understanding the ratings of social media comments can help both service providers as well as prospective customers who do not spend much time reading posts but want to understand the perspectives of others about a particular service/product. Additionally, predicting ratings of social media comments will help to build databases for recommender systems in different contexts.
Originality/value
The uniqueness of this study is in utilizing a combination of sentiment and emotion scores to predict the ratings of tweets related to different online services, namely, e-learning OFD and OTAs.
Details
Keywords
Priyadarshini R., Latha Tamilselvan and Rajendran N.
The purpose of this paper is to propose a fourfold semantic similarity that results in more accuracy compared to the existing literature. The change detection in the URL and the…
Abstract
Purpose
The purpose of this paper is to propose a fourfold semantic similarity that results in more accuracy compared to the existing literature. The change detection in the URL and the recommendation of the source documents is facilitated by means of a framework in which the fourfold semantic similarity is implied. The latest trends in technology emerge with the continuous growth of resources on the collaborative web. This interactive and collaborative web pretense big challenges in recent technologies like cloud and big data.
Design/methodology/approach
The enormous growth of resources should be accessed in a more efficient manner, and this requires clustering and classification techniques. The resources on the web are described in a more meaningful manner.
Findings
It can be descripted in the form of metadata that is constituted by resource description framework (RDF). Fourfold similarity is proposed compared to three-fold similarity proposed in the existing literature. The fourfold similarity includes the semantic annotation based on the named entity recognition in the user interface, domain-based concept matching and improvised score-based classification of domain-based concept matching based on ontology, sequence-based word sensing algorithm and RDF-based updating of triples. The aggregation of all these similarity measures including the components such as semantic user interface, semantic clustering, and sequence-based classification and semantic recommendation system with RDF updating in change detection.
Research limitations/implications
The existing work suggests that linking resources semantically increases the retrieving and searching ability. Previous literature shows that keywords can be used to retrieve linked information from the article to determine the similarity between the documents using semantic analysis.
Practical implications
These traditional systems also lack in scalability and efficiency issues. The proposed study is to design a model that pulls and prioritizes knowledge-based content from the Hadoop distributed framework. This study also proposes the Hadoop-based pruning system and recommendation system.
Social implications
The pruning system gives an alert about the dynamic changes in the article (virtual document). The changes in the document are automatically updated in the RDF document. This helps in semantic matching and retrieval of the most relevant source with the virtual document.
Originality/value
The recommendation and detection of changes in the blogs are performed semantically using n-triples and automated data structures. User-focussed and choice-based crawling that is proposed in this system also assists the collaborative filtering. Consecutively collaborative filtering recommends the user focussed source documents. The entire clustering and retrieval system is deployed in multi-node Hadoop in the Amazon AWS environment and graphs are plotted and analyzed.
Details
Keywords
Experienced journalists have labelled this the worst disinformation event they have experienced. The spread of inaccurate information online has made monitoring the unfolding…
Details
DOI: 10.1108/OXAN-DB283260
ISSN: 2633-304X
Keywords
Geographic
Topical
Evagelos Varthis and Marios Poulos
This study aims to present metaGraphos, a crowdsourcing system that aids in the transcription and semantic enhancement of scanned documents by using a pool of volunteers or people…
Abstract
Purpose
This study aims to present metaGraphos, a crowdsourcing system that aids in the transcription and semantic enhancement of scanned documents by using a pool of volunteers or people willing to participate in exchange for a financial reward.
Design/methodology/approach
The metaGraphos can be used in circumstances where optical character recognition fails to produce satisfactory results, semantic tagging or assigning thematic headings to texts is considered necessary or even when ground-truth data has to be collected in raw form.
Findings
The system automatically provides a Web-based interface comprising a static HTML page and JavaScript code that displays the scanned images of the document, coupled with the corresponding incomplete texts side by side, allowing users to correct or complete the texts in parallel.
Social implications
By assisting the parallel transcription and the semantic enhancement of difficult scanned documents, the system further reveals the hidden cultural wealth and aids in knowledge dissemination, a fact that contributes significantly to the academic-scientific dialog and feedback.
Originality/value
Individual researchers, libraries and organizations in general may benefit from the system because it is cost-effective, practical and simple to set up client–server architecture that provides a reliable way to transcribe texts or revise transcriptions on a large scale.
Details