This study aims to improve the television (TV) animation sound recommendation system's user experience through high performance computing technology. Firstly, the Collaborative Filtering (CF) algorithm, computer Sentiment Analysis (SA) method, and recommendation system evaluation methods are discussed to comprehend the SA process based on user and computer text. Secondly, according to the time series analysis of TV animation request information, a TV animation sound recommendation system is developed, integrating a model, CF, content-based filtering, and statistical methods to enhance the system's effectiveness. Finally, 136 TV animations from Tencent Video serve as experimental data samples to assess the performance of different recommendation algorithms within the TV animation recommendation system. The login times for non-registered users of the proposed system are also tested. The results show that the proposed system using a hybrid recommendation algorithm performs better in algorithm accuracy and recall, with recommendation accuracy and recall reaching 62.20% and 82.10%. The success rate of TV animation recommendations based on user expectation emotion is 100%. Therefore, the hybrid recommendation algorithm-based TV animation sound recommendation system can better reflect users’ evaluation of TV animation sound, providing users with better recommendation services.
LytvynVVysotskaVShatskykhV, et al.Design of a recommendation system based on collaborative filtering and machine learning considering personal needs of the user. East Eur J Enterp Technol2019; 4: 6–28.
2.
FayyazZEbrahimianMNawaraD, et al.Recommendation systems: algorithms, challenges, metrics, and business opportunities. Appl Sci2020; 10: 7748.
3.
SerranoW. Intelligent recommender system for big data applications based on the random neural network. Big Data Cognit Comput2019; 3: 15.
4.
DeldjooYDacremaMFConstantinMG, et al.Movie genome: alleviating new item cold start in movie recommendation. User Model User Adapt Interact2019; 29: 291–343.
5.
PiaoJZhangGXuF, et al.Bringing friends into the loop of recommender systems: an exploratory study. Proc ACM Hum Comput Interact2021; 5: 1–26.
6.
BaşarslanMSKayaalpF. Sentiment analysis on social media reviews datasets with deep learning approach. Sakarya Univ J Comput Inf Sci2021; 4: 35–49.
7.
SunHWangGXiaS. Text tendency analysis based on multi-granularity emotional chunks and integrated learning. Neural Comput Appl2021; 33: 8119–8129.
8.
RaiSChakravertyS. A survey on computational metaphor processing. ACM Comput Surv (CSUR)2020; 53: 1–37.
9.
OzolinsUHaleSChengX, et al.Translation and back-translation methodology in health research: a critique. Expert Rev Pharmacoeconomics Outcomes Res2020; 20: 69–77.
10.
MaoXChangSShiJ, et al.Sentiment-aware word embedding for emotion classification. Appl Sci2019; 9: 1334.
11.
AnvarjonTKwonS. Deep-net: a lightweight CNN-based speech emotion recognition system using deep frequency features. Sensors2020; 20: 5212.
12.
Sánchez-MorenoDLópez BatistaVVicenteMDM, et al.Exploiting the user social context to address neighborhood bias in collaborative filtering music recommender systems. Information2020; 11: 439.
13.
DarvishyAIbrahimHSidiF, et al.A customized non-exclusive clustering algorithm for news recommendation systems. J Univ Babylon Pure Appl Sci2019; 27: 368–379.
14.
LeeDNamKHanI, et al.From free to fee: monetizing digital content through expected utility-based recommender systems. Inf Manage2022; 59: 103681.
15.
WenX. Using deep learning approach and IoT architecture to build the intelligent music recommendation system. Soft Comput2021; 25: 3087–3096.
16.
LinWZhuMZhouX, et al.A deep neural collaborative filtering based service recommendation method with multi-source data for smart cloud-edge collaboration applications. Tsinghua Sci Technol2023; 29: 897–910.
17.
LiuKXueFGuoD, et al.MEGCF: multimodal entity graph collaborative filtering for personalized recommendation. ACM Trans Inf Syst2023; 41: 1–27.
18.
AresheyAMathkourH. Transfer learning for sentiment classification using bidirectional encoder representations from transformers (BERT) model. Sensors2023; 23: 5232.
19.
NemkulK. Use of bidirectional encoder representations from transformers (BERT) and robustly optimized BERT pretraining approach (RoBERTa) for Nepali news classification. Tribhuvan Univ J2024; 39: 124–137.
20.
SharmaKLeeYCNambiS, et al.A survey of graph neural networks for social recommender systems. ACM Comput Surv2024; 56: 1–34.
21.
JiYSunAZhangJ, et al.A critical study on data leakage in recommender system offline evaluation. ACM Trans Inf Syst2023; 41: 1–27.
22.
UmTOhBSeoB, et al.Fastflow: accelerating deep learning model training with smart offloading of input data pipeline. Proc VLDB Endow2023; 16: 1086–1099.
23.
Sánchez-RibesVMaciá-LilloAMoraH, et al.Efficient GPU cloud architectures for outsourcing high-performance processing to the cloud. Int J Adv Manuf Technol2024; 133: 949–958.
24.
MuYWuY. Multimodal movie recommendation system using deep learning. Mathematics2023; 11: 895.
25.
WangYYuWNiuL. Research on session recommendation system based on graph neural network. Adv Eng Technol Res2024; 10: 270–270.
26.
YinCShiLSunR, et al.Improved collaborative filtering recommendation algorithm based on differential privacy protection. J Supercomput2020; 76: 5161–5174.
27.
ChenJZhaoCChenL. Collaborative filtering recommendation algorithm based on user correlation and evolutionary clustering. Complex Intell Syst2020; 6: 147–156.
28.
ZhangPZhangZTianT, et al.Collaborative filtering recommendation algorithm integrating time windows and rating predictions. Appl Intell2019; 49: 3146–3157.
29.
JiangMZhangZJiangJ, et al.A collaborative filtering recommendation algorithm based on information theory and bi-clustering. Neural Comput Appl2019; 31(12): 8279–8287.
30.
LiuX. A collaborative filtering recommendation algorithm based on the influence sets of e-learning group’s behavior. Cluster Comput2019; 22: 2823–2833.
31.
NajafabadiMKMohamedAOnnCW. An impact of time and item influencer in collaborative filtering recommendations using graph-based model. Inf Process Manage2019; 56: 526–540.
32.
ChenW. A novel long short-term memory network model for multimodal music emotion analysis in affective computing. J Appl Sci Eng2022; 26: 367–376.
33.
FujiwaraTSakamotoNNonakaJ, et al.A visual analytics framework for reviewing multivariate time-series data with dimensionality reduction. IEEE Trans Visualization Comput Graphics2020; 27: 1601–1611.
34.
SeibertJKayCWMHuwerJ. EXPlainistry: creating documentation, explanations, and animated visualizations of chemistry experiments supported by information and communication technology to help school students understand molecular-level interactions. J Chem Educ2019; 96: 2503–2509.
35.
DeldjooYNoiaT DMerraF A. A survey on adversarial recommender systems: from attack/defense strategies to generative adversarial networks. ACM Comput Surv (CSUR), 2021, 54, pp.1–38.
