KSTAR: A Knowledge Based Approach for Socially Relevant Term Aggregation for Web Page Recommendation

Author(s):  
Deepak Surya ◽  
Gerard Deepak ◽  
A. Santhanavijayan
2010 ◽  
Author(s):  
Bryan Nation ◽  
Marshall Smith ◽  
Kanav Kahol

Symmetry ◽  
2021 ◽  
Vol 13 (10) ◽  
pp. 1772
Author(s):  
Amit Kumar Nandanwar ◽  
Jaytrilok Choudhary

Internet technologies are emerging very fast nowadays, due to which web pages are generated exponentially. Web page categorization is required for searching and exploring relevant web pages based on users’ queries and is a tedious task. The majority of web page categorization techniques ignore semantic features and the contextual knowledge of the web page. This paper proposes a web page categorization method that categorizes web pages based on semantic features and contextual knowledge. Initially, the GloVe model is applied to capture the semantic features of the web pages. Thereafter, a Stacked Bidirectional long short-term memory (BiLSTM) with symmetric structure is applied to extract the contextual and latent symmetry information from the semantic features for web page categorization. The performance of the proposed model has been evaluated on the publicly available WebKB dataset. The proposed model shows superiority over the existing state-of-the-art machine learning and deep learning methods.


Author(s):  
Amit Gupta ◽  
Rajesh Bhatia

Web Page Classification is decisive for information retrieval and management task and plays an imperative role for natural language processing (NLP) problems in web engineering. Traditional machine learning algorithms excerpt covet features from web pages whereas deep leaning algorithms crave features as the network goes deeper. Pre-trained models such as BERT attains remarkable achievement for text classification and continue to show state-ofthe-art results. Knowledge Graphs can provide rich structured factual information for better language modelling and representation. In this study, we proposed an ensemble Knowledge Based Deep Inception (KBDI) approachfor web page classification by learning bidirectional contextual representation using pre-trained BERT incorporating Knowledge Graph embeddings and fine-tune the target task by applying Deep Inception network utilizing parallel multi-scale semantics. Proposed ensemble evaluates the efficacy of fusing domain specific knowledge embeddings with the pre-trained BERT model. Experimental interpretation exhibit that the proposed BERT fused KBDI model outperforms benchmark baselines and achieve better performance in contrast to other conventional approaches evaluated on web page classification datasets.


2015 ◽  
Vol 10 (1) ◽  
pp. 75 ◽  
Author(s):  
Kimberly Miller

A Review of: Bowen, A. (2014). LibGuides and web-based library guides in comparison: Is there a pedagogical advantage? Journal of Web Librarianship, 8(2), 147-171. doi:10.1080/19322909.2014.903709 Abstract Objective – This study compares two versions of an online information literacy tutorial – one built with Springshare’s LibGuides and one built as a series of web pages – in order to determine if either platform provides a pedagogical advantage in delivering online instruction. Design – Experimental, posttest only. Setting – Large, public, primarily undergraduate four-year university in the Western United States of America with 16,000 full time equivalent student enrollment. Subjects – The sample consists of 812 students enrolled in 25 sections of a 100-level Communications Studies course. Of those students, 89 responded to the study’s posttest survey (11% response rate). Of the 89 respondents, 53 viewed the LibGuide tutorial: 12 respondents were male, 33 respondents were female, and 8 respondents did not report their gender. Of the 53 LibGuide participants, 47 responded to other demographic questions, and were primarily 18-20 years old (94%), first-year students (79%), and non-Communication Studies majors (91%). The remaining 36 respondents viewed the web page tutorial: 7 respondents were male, 25 respondents were female, and 4 did not report their gender. Of the 32 respondents that provided demographic information, all participants were 18-20 years old, 31 of 32 were first-year students, and the majority were non-Communication Studies majors (78%). Methods – Students completed an online tutorial designed to teach them information literacy skills necessary to find resources for a class debate. Each section was randomly assigned to one of two information literacy tutorials: 12 sections viewed a tutorial built with LibGuides and 13 sections viewed a web page tutorial. The two tutorials included identical instructional content and worksheet. Each of the tutorials’ six sections were tied to the ACRL Information Literacy Competency Standards for Higher Education. A seventh section in both tutorials administered a voluntary survey. Six knowledge-based survey questions tested students’ abilities on the six skills covered in the tutorials. Three affective questions asked students to use a four-point Likert scale to report ease (1 = very easy, 4 = very difficult), clarity (1 = very clear, 4 = very unclear), and convenience (1 = very convenient, 4 = very inconvenient) of six research skills, including: identifying keywords and main concepts in a topic, identifying scholarly versus non-scholarly sources, finding relevant scholarly articles, locating a book’s call number in the library catalog and on the shelf, finding newspaper articles, and constructing an annotated bibliography. Two affective survey questions asked students to use a four-point Likert scale (1 = very significant increase, 4 = no increase) to rate the impact the tutorial had on their knowledge of and satisfaction with using the library in each of the six areas of research. Main Results – The overall response patterns for the six information literacy knowledge-based questions were similar for both groups. Students who viewed the LibGuides tutorial performed better than the web page group on four of the six knowledge-based questions. The web page group performed better than the LibGuides group on two of the six knowledge-based questions. Across the board, students performed poorly on the first question, which measured students’ abilities to form a search string (39.2% correct in the LibGuides group; 25.7% correct in the web page group), and on the fifth question which asked students to identify the best source of current information from a list of resources (32% correct in the LibGuides group; 17% correct in the web page group). Response means on the first three affective questions indicate that students in both groups found searching for relevant scholarly articles and constructing an annotated bibliography to be more difficult than the other four skills. Additionally, students in the LibGuide group reported slightly higher means than the web page group concerning the clarity of finding newspaper articles, and were therefore less clear on the task. Students in the web page group reported slightly higher means than the LibGuide group when reporting the convenience of constructing an annotated bibliography, suggesting they found creating a bibliography more inconvenient. Students in both groups also responded similarly to the final two affective questions measuring the perceived impact the tutorial had on their knowledge of and satisfaction with using library resources.


2017 ◽  
Vol 9 (3) ◽  
pp. 2236-2244 ◽  
Author(s):  
PremSagar Sharma ◽  
Sharma A.K ◽  
Pankaj Garg

Sign in / Sign up

Export Citation Format

Share Document