scholarly journals Modeling user preference dynamics with coupled tensor factorization for social media recommendation

2020 ◽  
Author(s):  
Hamidreza Tahmasbi ◽  
Mehrdad Jalali ◽  
Hassan Shakeri
Keyword(s):  
Social Media ◽  
User Satisfaction ◽  
User Preferences ◽  
User Preference ◽  
Tensor Factorization ◽  
Plausible Assumption ◽  
The Past ◽  
Proposed Model ◽  
Recommendation Accuracy ◽  
Over Time

AbstractAn essential problem in real-world recommender systems is that user preferences are not static and users are likely to change their preferences over time. Recent studies have shown that the modelling and capturing the dynamics of user preferences lead to significant improvements on recommendation accuracy and, consequently, user satisfaction. In this paper, we develop a framework to capture user preference dynamics in a personalized manner based on the fact that changes in user preferences can vary individually. We also consider the plausible assumption that older user activities should have less influence on a user’s current preferences. We introduce an individual time decay factor for each user according to the rate of his preference dynamics to weigh the past user preferences and decrease their importance gradually. We exploit users’ demographics as well as the extracted similarities among users over time, aiming to enhance the prior knowledge about user preference dynamics, in addition to the past weighted user preferences in a developed coupled tensor factorization technique to provide top-K recommendations. The experimental results on the two real social media datasets—Last.fm and Movielens—indicate that our proposed model is better and more robust than other competitive methods in terms of recommendation accuracy and is more capable of coping with problems such as cold-start and data sparsity.

scholarly journals Accuracy improvements for cold-start recommendation problem using indirect relations in social networks

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Fu Jie Tey ◽  
Tin-Yu Wu ◽  
Chiao-Ling Lin ◽  
Jiann-Liang Chen
Keyword(s):  
Social Media ◽  
Recommender System ◽  
Mobile Networks ◽  
Reference Value ◽  
User Preferences ◽  
Digital Information ◽  
Internet Applications ◽  
Social Media Networks ◽  
Recommendation Accuracy ◽  
Gain Access

AbstractRecent advances in Internet applications have facilitated information spreading and, thanks to a wide variety of mobile devices and the burgeoning 5G networks, users easily and quickly gain access to information. Great amounts of digital information moreover have contributed to the emergence of recommender systems that help to filter information. When the rise of mobile networks has pushed forward the growth of social media networks and users get used to posting whatever they do and wherever they visit on the Web, such quick social media updates already make it difficult for users to find historical data. For this reason, this paper presents a social network-based recommender system. Our purpose is to build a user-centered recommender system to exclude the products that users are disinterested in according to user preferences and their friends' shopping experiences so as to make recommendations effective. Since there might be no corresponding reference value for new products or services, we use indirect relations between friends and “friends’ friends” as well as sentinel friends to improve the recommendation accuracy. The simulation result has proven that our proposed mechanism is efficient in enhancing recommendation accuracy.

scholarly journals Predicting Implicit User Preferences with Multimodal Feature Fusion for Similar User Recommendation in Social Media

2021 ◽  
Vol 11 (3) ◽  
pp. 1064
Author(s):  
Jenq-Haur Wang ◽  
Yen-Tsang Wu ◽  
Long Wang
Keyword(s):  
Social Media ◽  
Feature Fusion ◽  
Relevant Information ◽  
Image Features ◽  
User Preferences ◽  
User Preference ◽  
Late Fusion ◽  
Multimodal Features ◽  
Fusion Methods ◽  
Text Features

In social networks, users can easily share information and express their opinions. Given the huge amount of data posted by many users, it is difficult to search for relevant information. In addition to individual posts, it would be useful if we can recommend groups of people with similar interests. Past studies on user preference learning focused on single-modal features such as review contents or demographic information of users. However, such information is usually not easy to obtain in most social media without explicit user feedback. In this paper, we propose a multimodal feature fusion approach to implicit user preference prediction which combines text and image features from user posts for recommending similar users in social media. First, we use the convolutional neural network (CNN) and TextCNN models to extract image and text features, respectively. Then, these features are combined using early and late fusion methods as a representation of user preferences. Lastly, a list of users with the most similar preferences are recommended. The experimental results on real-world Instagram data show that the best performance can be achieved when we apply late fusion of individual classification results for images and texts, with the best average top-k accuracy of 0.491. This validates the effectiveness of utilizing deep learning methods for fusing multimodal features to represent social user preferences. Further investigation is needed to verify the performance in different types of social media.

scholarly journals Learning Personalized End-to-End Goal-Oriented Dialog

2019 ◽  
Vol 33 ◽  
pp. 6794-6801 ◽  
Author(s):  
Liangchen Luo ◽  
Wenhao Huang ◽  
Qi Zeng ◽  
Zaiqing Nie ◽  
Xu Sun
Keyword(s):  
User Satisfaction ◽  
State Of The Art ◽  
User Preferences ◽  
Task Completion ◽  
Dialog Systems ◽  
Performance Improvements ◽  
Human Evaluation ◽  
Proposed Model ◽  
End To End ◽  
Qualitative Performance

Most existing works on dialog systems only consider conversation content while neglecting the personality of the user the bot is interacting with, which begets several unsolved issues. In this paper, we present a personalized end-to-end model in an attempt to leverage personalization in goal-oriented dialogs. We first introduce a PROFILE MODEL which encodes user profiles into distributed embeddings and refers to conversation history from other similar users. Then a PREFERENCE MODEL captures user preferences over knowledge base entities to handle the ambiguity in user requests. The two models are combined into the PERSONALIZED MEMN2N. Experiments show that the proposed model achieves qualitative performance improvements over state-of-the-art methods. As for human evaluation, it also outperforms other approaches in terms of task completion rate and user satisfaction.

How Do Adolescents Get Their E-Cigarettes and Other Electronic Vaping Devices?

2018 ◽  
Vol 33 (3) ◽  
pp. 420-429 ◽  
Author(s):  
Jessica K. Pepper ◽  
Ellen M. Coats ◽  
James M. Nonnemaker ◽  
Brett R. Loomis
Keyword(s):  
Social Media ◽  
Logistic Regression ◽  
Social Experience ◽  
Completion Rate ◽  
Future Research ◽  
Social Situations ◽  
Cross Sectional Survey ◽  
Cross Sectional ◽  
The Past ◽  
Over Time

Purpose: More adolescents “vape” (use e-cigarettes and similar devices) than smoke, but little is known about how underage users obtain vaping devices. This knowledge could inform efforts to prevent youth access. Design: Original cross-sectional survey with social media recruitment. Settings: Online. Participants: A total of 1729 adolescents (2809 qualified on screener; completion rate 61.6%) aged 15 to 17 years who vaped in the past 30 days. Measures: Adolescents’ vaping attitudes, ownership of vaping devices, how they obtain devices, and frequency of borrowing others’ devices. Analysis: Logistic regression. Results: Most adolescents (78.2%) owned a vaping device. The most common sources were purchasing from a store or online (31.1%), buying from another person (16.3%), or giving someone money to purchase for them (15.0%). The majority (72.8%) had used someone else’s vaping device in the past 30 days. Adolescents who vaped more often, did not own a vaping device, vaped in social situations, and had previously been refused purchase were more likely to frequently borrow others’ devices. Conclusions: Despite high rates of ownership, many adolescents borrowed devices, suggesting that borrowing is part of users’ social experience, not just a means of acquisition. Although better enforcement of age restrictions could lessen purchasing, future research is needed to understand why adolescents borrow and how their acquisition sources shift over time. That information could be harnessed for targeted, borrowing-related antivaping campaigns.

Personalization Approaches for Ranking

2017 ◽  
Vol 7 (1) ◽  
pp. 1-16
Author(s):  
Madhuri A. Potey ◽  
Pradeep K. Sinha
Keyword(s):  
User Satisfaction ◽  
State Of The Art ◽  
User Model ◽  
Research Trends ◽  
User Preferences ◽  
Machine Learning Algorithms ◽  
User Preference ◽  
Information Need ◽  
And Behavior ◽  
Available Information

Search engine technologies are evolving to satisfy the user's ever increasing information need; but are yet to achieve perfection especially in ranking. With the exponential growth in the available information on the internet; ranking has become vital for satisfactory search experience. User satisfaction can be ensured to some extent by personalizing the search results based on user preferences which can be explicitly stated or learned from user's search behavior. Machine learning algorithms which predict user preference from the available information related to the user are extensively experimented for personalization. Among several studies undertaken for re-ranking the documents, many focus on the user. Such approaches create user model to capture the search context and behavior. This study attempts to analyze the research trends in user model based personalization and discuss experimental results in personalized information retrieval area. The authors experimented to extend the state of the art in the specific areas of personalization.

scholarly journals Secure Vertical Handover to NEMO Using Hybrid Cryptosystem

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Vikram Raju Reddicherla ◽  
Umashankar Rawat ◽  
Y. Jeevan Nagendra Kumar ◽  
Atef Zaguia
Keyword(s):  
Security Analysis ◽  
Signal Strength ◽  
Vertical Handover ◽  
Received Signal Strength ◽  
User Preferences ◽  
User Preference ◽  
Network Selection ◽  
Selection Mechanism ◽  
Proposed Model ◽  
Correspondent Node

To provide security to all pairs of nodes in network mobility (NEMO) while executing the handoff between different technologies, a hybrid cryptosystem with a suitable network selection mechanism is proposed. All pairs of nodes, i.e., Mobile Node (MN), Mobile Router (MR), Correspondent Node (CN) and MN, and Home Agent (HA), respectively, are considered. A proper security mechanism is proposed to provide confidentiality to Bound Update (BU) during handoff and conversation between MN, MR, and HA using the elliptic curve cryptography (ECC). In this solution, a network selection mechanism is proposed based on user preference and Received Signal Strength (RSS) in a heterogeneous network. The proposed model can protect the communication using security analysis from all NEMO standard attacks. Whenever NEMO moves, MR intimates to HA about the address change using (BU) and MR receives Binding Acknowledgement (BA) as a reply. During data (frame) exchange and registration between MN, CN, and HA, various security threats arise. In the earlier work, only the security solution is given, and the best network selection algorithm is not provided in a heterogeneous environment. Therefore, in this paper, the best network selection is contributed based on Received Signal Strength (RSS) and user preferences. A comparison of the proposed model is drawn with Return Routability Procedure (RRP). Authentication is provided for communication between MN and CN. The proof is derived using BAN logic. Many standard security attacks have been successfully avoided on all pairs of communications. It has been observed that the proposed model achieves 2.4854% better throughput than the existing models. Also, the proposed model reduces the handoff latency and packet loss by 2.7482% and 3.8274%, respectively.

scholarly journals Accuracy Improvements for Cold-Start Recommendation Problem using Indirect Relations in Social Networks

2020 ◽  
Author(s):  
Fu Jie Tey ◽  
Tin-Yu Wu ◽  
Chiao-Ling Lin ◽  
Jiann-Liang Chen
Keyword(s):  
Social Media ◽  
Recommender System ◽  
Mobile Networks ◽  
Information Filtering ◽  
Reference Value ◽  
User Preferences ◽  
Digital Information ◽  
Internet Applications ◽  
Social Media Networks ◽  
Recommendation Accuracy

Abstract Recent advances on Internet applications have facilitated information spreading. Thanks to a wide variety of mobile devices and the burgeoning 5G networks, users gain access easily and quickly to information. Also, the great amount of digital information has contributed to the emergence of recommender systems that help information filtering. As the rise of mobile networks has pushed forward the growth of social media networks, users have gotten used to posting whatever they do and wherever they visit on the Web. Nevertheless, quick social media updates can make it difficult for users to find historical data. For this reason, this paper presents a social network-based recommender system. Our purpose is to build a user-centered recommender system to exclude the products that users are disinterested in according to user preferences and their friends' shopping experiences so as to make recommendations effective. There is normally no corresponding reference value for new products or services, so we use the indirect relations between friends and "friends’ friends" as well as sentinel friends to improve the recommendation accuracy. Our proposed mechanism has been proven efficient in enhancing recommendation accuracy.

Design and Manufacturing of 3D Printed Foods With User Validation

2020 ◽  
Author(s):  
Stefania Chirico Scheele ◽  
Martin Binks ◽  
Paul F. Egan
Keyword(s):  
Additive Manufacturing ◽  
User Satisfaction ◽  
Three Dimensional ◽  
User Preferences ◽  
User Preference ◽  
Great Promise ◽  
High Fidelity ◽  
Standard Design ◽  
3D Printed ◽  
Overhang Angle

Abstract Additive manufacturing is becoming widely practical for diverse engineering applications, with emerging approaches showing great promise in the food industry. From the realization of complex food designs to the automated preparation of personalized meals, 3D printing promises many innovations in the food manufacturing sector. However, its use is limited due to the need to better understand manufacturing capabilities for different food materials and user preferences for 3D food prints. Our study aims to explore the 3D food printability of design features, such as overhangs and holes, and assess how well they print through quantitative and qualitative measurements. Designs with varied angles and diameters based on the standard design limitations for additive manufacturing were printed and measured using marzipan and chocolate. It was found that marzipan material has a minimum feature size for overhang design at 55° and for hole design at 4mm, while chocolate material has a minimum overhang angle size of 35° and does not reliably print holes. Users were presented a series of designs to determine user preference (N = 30) towards the importance of fidelity and accuracy between the expected design and the 3D printed sample, and how much they liked each sample. Results suggest that users prefer designs with high fidelity to their original shape and perceive the current accuracy/precision of 3D printers sufficient for accurately printing three-dimensional geometries. These results demonstrate the current manufacturing capabilities for 3D food printing and success in achieving high fidelity designs for user satisfaction. Both of these considerations are essential steps in providing automated and personalized manufacturing for specific user needs and preferences.

scholarly journals A Technique of Recursive Reliability-Based Missing Data Imputation for Collaborative Filtering

2021 ◽  
Vol 11 (8) ◽  
pp. 3719
Author(s):  
Sun-Young Ihm ◽  
Shin-Eun Lee ◽  
Young-Ho Park ◽  
Aziz Nasridinov ◽  
Miyeon Kim ◽  
...  
Keyword(s):  
Missing Data ◽  
Collaborative Filtering ◽  
State Of The Art ◽  
High Reliability ◽  
User Preferences ◽  
User Preference ◽  
Data Imputation ◽  
Missing Data Imputation ◽  
Common Interests ◽  
Recommendation Accuracy

Collaborative filtering (CF) is a recommendation technique that analyzes the behavior of various users and recommends the items preferred by users with similar preferences. However, CF methods suffer from poor recommendation accuracy when the user preference data used in the recommendation process is sparse. Data imputation can alleviate the data sparsity problem by substituting a virtual part of the missing user preferences. In this paper, we propose a k-recursive reliability-based imputation (k-RRI) that first selects data with high reliability and then recursively imputes data with additional selection while gradually lowering the reliability criterion. We also propose a new similarity measure that weights common interests and indifferences between users and items. The proposed method can overcome disregarding the importance of missing data and resolve the problem of poor data imputation of existing methods. The experimental results demonstrate that the proposed approach significantly improves recommendation accuracy compared to those resulting from the state-of-the-art methods while demanding less computational complexity.

scholarly journals User Preference Dynamics on Evolving Social Networks - Learning, Modeling and Prediction

2019 ◽  
Author(s):  
Fabiola S. F. Pereira ◽  
Gina M. B. Oliveira ◽  
João Gama
Keyword(s):  
Social Networks ◽  
Network Structure ◽  
Online Social Networks ◽  
Temporal Dynamics ◽  
User Preferences ◽  
User Preference ◽  
Modeling And Prediction ◽  
Social Network Structure ◽  
Rich Information ◽  
Over Time

The preferences adopted by individuals are constantly modified as these are driven by new experiences, natural life evolution and, mainly, influence from friends. Studying these temporal dynamics of user preferences has become increasingly important for personalization tasks. Online social networks contain rich information about social interactions and relations, becoming essential source of knowledge for the understanding of user preferences evolution. In this thesis, we investigate the interplay between user preferences and social networks over time. We use temporal networks to analyze the evolution of social relationships and propose strategies to detect changes in the network structure based on node centrality. Our findings show that we can predict user preference changes by just observing how her social network structure evolves over time.

Sign in / Sign up

Export Citation Format

Share Document