Improved content recommendation algorithm integrating semantic information
TL;DR: Wang et al. as discussed by the authors improved the semantic analysis ability of the traditional content-based recommendation algorithm by integrating semantic information with TF-IDF vector space model for item modeling and similarity calculation.
read more
Abstract: Abstract Content-based recommendation technology is widely used in the field of e-commerce and education because of its intuitive and easy to explain advantages. However, due to the congenital defect of insufficient semantic analysis of TF-IDF vector space model, the traditional content-based recommendation technology has the problem of insufficient semantic analysis in item modeling, fails to consider the role of semantic information in knowledge expression and similarity calculation, and is not accurate enough in calculating item content similarity. The items with semantic relevance in content can not be well mined. The research goal of this paper is to improve the semantic analysis ability of the traditional content-based recommendation algorithm by integrating semantic information with TF-IDF vector space model for item modeling and similarity calculation and proposed an improved content recommendation algorithm integrating semantic information. In order to prove the effectiveness of the proposed method, several groups of experiments are carried out. The experiments results showed that the overall performance of the proposed algorithm in this paper is the best and relatively stable. This verified the validity of our method.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Relevance Detection using Text Entailment for Health-related Question-Answer Texts with Imbalanced Data
Marina Irdayanti,Diana Purwitasari,Daniel Siahaan +2 more
- 10 Jul 2024
TL;DR: This study proposes a relevance detection system using text entailment for health-related Q&A texts with imbalanced data, leveraging finetuned IndoBERT-QA model to achieve higher accuracy (0.91) compared to BERT (0.87) in Indonesian language.
LLMTrajQuery: an LLM-based generative approach to semantic trajectory queries
Shu-tong Yu,Junnan Liu,Chenchen Gao,Weifan Niu,Xuan Guo,Haiyan Liu,Mingliang Xu,Shu-tong Yu,Junnan Liu,Chenchen Gao,Weifan Niu,Xuan Guo,Haiyan Liu,Mingliang Xu +13 more
Automated generation of educational content based on semantic analysis
Weifeng Deng,Lin Wang,Xue Deng,Weifeng Deng,Lin Wang,Xue Deng +5 more
Abstract: In the digital era, the application of artificial intelligence in education has brought revolutionary changes. Personalized and intelligent generation of educational content is key to enhancing teaching efficiency and the learning experience. Traditional methods of generating educational content suffer from inefficiency and a lack of personalization. To address these issues, this study proposes a method for the automated generation of educational content based on semantic analysis, aimed at improving the quality and efficiency of content generation. Initially, the research explores semantic analysis of educational content based on knowledge extraction, introducing a novel lightweight semantic analysis model capable of efficiently extracting key knowledge points from educational materials. Subsequently, the study investigates a semantic analysis-based content generation approach, utilizing masked semantic style encoding and an innovative method for indiscriminate semantic stylization of text generation to achieve consistent and personalized educational content output. These methods not only reduce the demand for computational resources but also enhance the level of content personalization. Overall, the proposed methods provide new technical avenues for the generation of intelligent educational content and lay the groundwork for the development of personalized educational resources to meet the diverse needs of learners. This has significant theoretical and practical value for advancing innovation and development in educational technology.
Development of Ilocos Sur Viajefy: A Tourism Information System Using Modified Text Frequency-Inverse Document Frequency Text Mining
Arpee Callejo Arruejo,Richard Copuz Arruejo +1 more
- 01 Jan 2023
TL;DR: The development of Ilocos Sur Viajefy, a tourism information system, incorporates the TF-IDF algorithm to recommend attractions and establishments based on user preferences. The system achieved high accuracy, precision, and recall with a "Very Highly Acceptable" rating.
References
•Proceedings Article
Efficient Estimation of Word Representations in Vector Space
Tomas Mikolov,Kai Chen,Greg S. Corrado,Jeffrey Dean +3 more
- 16 Jan 2013
TL;DR: Two novel model architectures for computing continuous vector representations of words from very large data sets are proposed and it is shown that these vectors provide state-of-the-art performance on the authors' test set for measuring syntactic and semantic word similarities.
27.5K
•Posted Content
Distributed Representations of Words and Phrases and their Compositionality
TL;DR: In this paper, the Skip-gram model is used to learn high-quality distributed vector representations that capture a large number of precise syntactic and semantic word relationships and improve both the quality of the vectors and the training speed.
Bag of Tricks for Efficient Text Classification
Armand Joulin,Edouard Grave,Piotr Bojanowski,Tomas Mikolov +3 more
- 01 Apr 2017
TL;DR: FastText as mentioned in this paper explores a simple and efficient baseline for text classification, which is often on par with deep learning classifiers in terms of accuracy and many orders of magnitude faster for training and evaluation.
•Posted Content
Graph Neural Networks in Recommender Systems: A Survey
TL;DR: This article provides a taxonomy of GNN-based recommendation models according to the types of information used and recommendation tasks and systematically analyze the challenges of applying GNN on different types of data.
1K
Text Mining: Use of TF-IDF to Examine the Relevance of Words to Documents
Shahzad Qaiser,Ramsha Ali +1 more
TL;DR: In this paper, the use of TF-IDF stands for (term frequencyinverse document frequency) is discussed in examining the relevance of key-words to documents in corpus in order to verify the findings from executing the algorithm.