Recommending Videos in Cold Start With Automatic Visual Tags

Elahi, Mehdi; Moghaddam, Farshad Bakhshandegan; Hosseini, Reza; Rimaz, Mohammad Hossein; Ioini, Nabil El; Tkalčič, Marko; Trattner, Christoph; Tillo, Tammam

doi:10.1145/3450614.3461687

Cited by 6 publications

(12 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, in domains rich in information density like education or news, textual features appear to provide the most valuable content description (Luo et al, 2008 ; Chantanurak et al, 2016 ; Kimoto et al, 2016 ; Tavakoli et al, 2020 ). In contrast, in entertainment domains, especially visual features appear to offer a good basis for calculation of recommendations (Deldjoo et al, 2016 , 2018b ; Lee and Abu-El-Haija, 2017 ; Elahi et al, 2020 , 2021 ; Yi et al, 2022 ).…”

Section: Discussionmentioning

confidence: 99%

“…High-level visual features such as faces, objects, and recognized celebrities were automatically extracted in Elahi et al ( 2021 ), to create vector representations for videos using a combination of term frequency-inverse document frequency (TF-IDF) (Sammut and Webb, 2010 ) and word2vec (Mikolov et al, 2013 ). TF-IDF is a statistical measure that reflects the importance of terms within a document or catalog, while word2vec describes a DNN technique used in Natural Language Processing (NLP) to learn word relationships.…”

Section: Video Recommender Systemsmentioning

confidence: 99%

“…A predominantly used algorithm in content-based video recommendation is k-Nearest-Neighbors (kNN) (Luo et al, 2008 ; Zhu et al, 2013 ; Elahi et al, 2017 , 2020 , 2021 ; Lee and Abu-El-Haija, 2017 ; Deldjoo et al, 2018a ; Hazrati and Elahi, 2021 ), which identifies the k most similar items, given a distance metric applied to the item features (Jannach et al, 2011b ). Items are more similar, the lower the distance between them.…”

Section: Video Recommender Systemsmentioning

confidence: 99%

“…Advertisement Textual Kaklauskas et al, 2018;Kim et al, 2021Education Textual Chantanurak et al, 2016Kimoto et al, 2016;Tavakoli et al, 2020;Leite et al, 2022 Movies and Series Aural Deldjoo et al, 2018a;Rimaz et al, 2021;Chakder et al, 2022;Pingali et al, 2022;Mondal et al, 2023 Textual Öztürk andKesim Cicekli, 2011;Zhu et al, 2013;Vizine Pereira and Hruschka, 2015;Wang et al, 2015Wang et al, , 2021Gomez-Uribe and Hunt, 2016;Elahi et al, 2017;Lu et al, 2017;Wei et al, 2017;Liu et al, 2019b;Kvifte et al, 2021;Zhuo et al, 2021;Chakder et al, 2022;Pingali et al, 2022;Mondal et al, 2023Visual Zhu et al, 2013Deldjoo et al, 2016Deldjoo et al, , 2018aElahi et al, 2017Elahi et al, , 2020Elahi et al, , 2021Hazrati and Elahi, 2021;Kvifte et al, 2021;Wang et al, 2021;Chakder et al, 2022;Pingali et al, 2022;Mondal et al, 2023 News Aural Luo et al, 2008Textual Luo et al, 2008Hopfgartner and…”

Section: Domain Features Referencesmentioning

confidence: 99%

See 3 more Smart Citations

An overview of video recommender systems: state-of-the-art and research issues

Lubos,

Felfernig,

Tautschnig

2023

Front. Big Data

View full text Add to dashboard Cite

Video platforms have become indispensable components within a diverse range of applications, serving various purposes in entertainment, e-learning, corporate training, online documentation, and news provision. As the volume and complexity of video content continue to grow, the need for personalized access features becomes an inevitable requirement to ensure efficient content consumption. To address this need, recommender systems have emerged as helpful tools providing personalized video access. By leveraging past user-specific video consumption data and the preferences of similar users, these systems excel in recommending videos that are highly relevant to individual users. This article presents a comprehensive overview of the current state of video recommender systems (VRS), exploring the algorithms used, their applications, and related aspects. In addition to an in-depth analysis of existing approaches, this review also addresses unresolved research challenges within this domain. These unexplored areas offer exciting opportunities for advancements and innovations, aiming to enhance the accuracy and effectiveness of personalized video recommendations. Overall, this article serves as a valuable resource for researchers, practitioners, and stakeholders in the video domain. It offers insights into cutting-edge algorithms, successful applications, and areas that merit further exploration to advance the field of video recommendation.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Video Recommender Systemsmentioning

confidence: 99%

Section: Video Recommender Systemsmentioning

confidence: 99%

Section: Domain Features Referencesmentioning

confidence: 99%

See 2 more Smart Citations

An overview of video recommender systems: state-of-the-art and research issues

Lubos,

Felfernig,

Tautschnig

2023

Front. Big Data

View full text Add to dashboard Cite

show abstract

“…Further, Elahi and their collegaues [48] argued that the goal of the recommendation system is to provide the users with high-quality content by minimizing their efforts to search for it. YouTube tries to anticipate what a user would like to see next based on what they have already watched.…”

Section: H4mentioning

confidence: 99%

How do Students Perceive Artificial Intelligence in YouTube Educational Videos Selection? A Case Study of Al Ain City

Farhi

Jeljeli²,

Hamdi

2022

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

This research focused on the students' perceptions of the role of Artificial Intelligence in the educational content recommendation system by using the SEM- Artificial Neural Network approach. Data obtained from structured surveys indicated that Artificial Intelligence plays a significant role in the educational content recommendation process. Most relationships proposed in the conceptual model remained significant, with p values as strong as p> 0.000. Further, the IPMA and ANN also revealed in-depth results. Thus, this research concludes that the video recommendation system is helping young students to search for and find the educational content they want. Besides, this system also provides them with a searching facility with fewer efforts, adding more value to YouTube as one of the most prominent digital platforms today.

show abstract