News Recommendation Using Semantics with the Bing-SF-IDF Approach

Hogenboom, Frederik; Capelle, Michel; Moerland, Marnix

doi:10.1007/978-3-319-14139-8_18

Cited by 5 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where sim Bing (u, v) and sim sf −idf + (u, v) represent the normalized Bing and SF-IDF+ similarity scores, and α is a weight optimized on the training set. This approach of enhancing semantics-driven recommender systems with named entity similarities using the Bing page counts are prototypical also for other models, such as Bing-SF-IDF [71], Bing-CF-IDF+ [17], or Bing-CSF-IDF+ [161].…”

Section: S(s)mentioning

confidence: 99%

“…In this context, one approach to address this issue is the inclusion of temporal constraints to model the limited validity of knowledge base items determined by the dynamic nature of events described in the news. Among the existing recommender systems, the ones included in the Hermes News Portal [17,[26][27][28]40,55,64,71,112,161] support knowledge base updates. More specifically, the Hermes framework not only provides the functionality for specifying temporal constraints of news items, but it also incorporates updates to the knowledge base based on event rules, meant to reflect changes of real-world events [53].…”

Section: Sequential and Timely Recommendationsmentioning

confidence: 99%

See 1 more Smart Citation

A survey on knowledge-aware news recommender systems

Iana

Alam

Paulheim

2024

View full text Add to dashboard Cite

News consumption has shifted over time from traditional media to online platforms, which use recommendation algorithms to help users navigate through the large incoming streams of daily news by suggesting relevant articles based on their preferences and reading behavior. In comparison to domains such as movies or e-commerce, where recommender systems have proved highly successful, the characteristics of the news domain (e.g., high frequency of articles appearing and becoming outdated, greater dynamics of user interest, less explicit relations between articles, and lack of explicit user feedback) pose additional challenges for the recommendation models. While some of these can be overcome by conventional recommendation techniques, injecting external knowledge into news recommender systems has been proposed in order to enhance recommendations by capturing information and patterns not contained in the text and metadata of articles, and hence, tackle shortcomings of traditional models. This survey provides a comprehensive review of knowledge-aware news recommender systems. We propose a taxonomy that divides the models into three categories: neural methods, non-neural entity-centric methods, and non-neural path-based methods. Moreover, the underlying recommendation algorithms, as well as their evaluations are analyzed. Lastly, open issues in the domain of knowledge-aware news recommendations are identified and potential research directions are proposed.

show abstract

Section: S(s)mentioning

confidence: 99%

Section: Sequential and Timely Recommendationsmentioning

confidence: 99%

A survey on knowledge-aware news recommender systems

Iana

Alam

Paulheim

2024

View full text Add to dashboard Cite

show abstract

“…They extend the synonym sets of concepts in news by adding other concepts in WordNet that have relationships with the included concepts. Based on aforementioned approaches, the family of CF-IDF is expanded by a set of later works [9,15,24,51,52].…”

Section: Feature-based News Modelingmentioning

confidence: 99%

Personalized News Recommendation: Methods and Challenges

Wu¹,

Wu²,

Huang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Personalized news recommendation is an important technique to help users find their interested news information and alleviate their information overload. It has been extensively studied over decades and has achieved notable success in improving users' news reading experience. However, there are still many unsolved problems and challenges that need to be further studied. To help researchers master the advances in personalized news recommendation over the past years, in this paper we present a comprehensive overview of personalized news recommendation. Instead of following the conventional taxonomy of news recommendation methods, in this paper we propose a novel perspective to understand personalized news recommendation based on its core problems and the associated techniques and challenges. We first review the techniques for tackling each core problem in a personalized news recommender system and the challenges they face. Next, we introduce the public datasets and evaluation metrics used for personalized news recommendation. We then discuss the key points on improving the responsibility of personalized news recommender systems. Finally, we raise several research directions that are worth investigating in future. This paper can provide up-to-date and comprehensive views to help readers understand the personalized news recommendation field. We hope this paper can facilitate research on personalized news recommendation and as well as related fields in natural language processing and data mining.

show abstract

“…While two identical documents have a Hellinger distance of 0, this is transformed via the similarity measure S(P,Q) = 1 -H(P,Q). Source: author, based on Kim, Park and Yoon (2016) Computing the term frequency-inverse document frequency (tf-idf) consists of two parts: the term frequency ( , ) and the inverse document frequency ( , ) (Hogenboom, Capelle and Moerland, 2014). First, the term frequency computes the frequency n of terms t ∈ in document d ∈ .…”

Section: Figure 1: Calculation Of Similarity Matrix Between Documentsmentioning

confidence: 99%

What are the main determinants of diffusion speed between academic research and industrial application? Evidence from four major clean-energy technologies

Probst

Anadón

Kontoleon

2021

Preprint

View full text Add to dashboard Cite

Recent evidence suggests a slowdown of economic productivity in major Western and Asian economies. One of the most convincing causes is the slowdown in research productivity in key sectors of the economy, such as low-carbon technologies. The latter trend is particularly worrying as low-carbon technologies play a critical role in keeping global warming well below the 2°C that the Paris Agreement set. We rely on a novel data science method that connects scientific articles with patented technologies. We extract the scientific publications cited in more than 600,000 clean energy technologies (wind, solar, biomass, li-ion) and investigate what determines the diffusion speed between scientific research and patented technologies. We demonstrate that the higher the quality of the scientific article (measured by citations), the lower the distance between scientists and inventors, and the higher the similarity between the content of the scientific article and the patent, the faster the diffusion between research and application. Yet, we also show that while more dissimilar content takes longer to be used in patents, the eventual impact of the patent is greater, possibly because it is more innovative. Our data also reveals that while distance appears to matter for the speed of knowledge diffusion, patents in the four low-carbon technologies on average rely on 81% of foreign sources of science, as scientific knowledge diffuses widely across the world economy. China and the United States play an outsized role as the source of scientific publications used in clean-technology patents globally. Nevertheless, while research is characterised by global spillovers, the application of such knowledge (in a patent) appears to be dominated by national teams, potentially due to greater local spillovers and secrecy issues.

show abstract

News Recommendation Using Semantics with the Bing-SF-IDF Approach

Cited by 5 publications

References 10 publications

A survey on knowledge-aware news recommender systems

A survey on knowledge-aware news recommender systems

Personalized News Recommendation: Methods and Challenges

What are the main determinants of diffusion speed between academic research and industrial application? Evidence from four major clean-energy technologies

Contact Info

Product

Resources

About