A User Influence Rank Algorithm Based on Interaction Behaviors in Cyber Group Events

2019 ◽  
Author(s):  
Jiangpeng Lin ◽  
Yu Wu ◽  
Li Wang ◽  
Weidong Ai ◽  
Yan Zeng
Keyword(s):  
User Influence ◽  
Interaction Behaviors

scholarly journals An Information Recommendation Technique Based on Influence and Activeness of Users in Social Networks

2021 ◽  
Vol 11 (6) ◽  
pp. 2530
Author(s):  
Minsoo Lee ◽  
Soyeon Oh
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Recommendation Systems ◽  
Network Services ◽  
The Past ◽  
User Behaviors ◽  
User Influence ◽  
User Activity ◽  
Information Recommendation ◽  
Social Network Services

Over the past few years, the number of users of social network services has been exponentially increasing and it is now a natural source of data that can be used by recommendation systems to provide important services to humans by analyzing applicable data and providing personalized information to users. In this paper, we propose an information recommendation technique that enables smart recommendations based on two specific types of analysis on user behaviors, such as the user influence and user activity. The components to measure the user influence and user activity are identified. The accuracy of the information recommendation is verified using Yelp data and shows significantly promising results that could create smarter information recommendation systems.

User Influence Analysis Based on Blogs

2016 ◽  
Author(s):  
Xiang LIU ◽  
Yan JIA ◽  
Rong JIANG ◽  
Yong QUAN
Keyword(s):  
Influence Analysis ◽  
User Influence

A Randomized Pilot Study of Rhythm-Based Music with Movement Strategies on Stress and Interaction Behaviors of Infant Caregivers

2021 ◽  
Vol 13 (1) ◽  
pp. 7-19
Author(s):  
Kamile Geist ◽  
Peggy Zoccola ◽  
Nathan Andary ◽  
Eugene Geist ◽  
Godwin Dogbey ◽  
...  
Keyword(s):  
Pilot Study ◽  
Salivary Cortisol ◽  
Parental Stress ◽  
Stress Hormones ◽  
Stress Hormone ◽  
Social Emotional ◽  
Positive Interaction ◽  
Movement Strategies ◽  
The Impact ◽  
Interaction Behaviors

Consistent, prolonged, and nurturing interactions of a primary caregiver with an infant is necessary for optimal development of the infant. Lowering parental stress can promote positive caregiver-infant social interaction behaviors. Studies show that when caregivers use rhythm-based music and movement strategies during interactions with their infants, non-verbal communication, mutual attunement, and self-reported stress levels improve. The purpose of this pilot study was to determine caregiver benefits (stress hormones and positive interaction behaviors) when learning rhythm-based music with movement strategies while interacting with their infant. This was achieved through randomization of caregiver/infant dyads to a treatment (instructional intervention) or control condition with no instruction. Significantly lower salivary cortisol levels and lower salivary cortisol/DHEA ratio values pre-post were observed for the treatment condition as compared to control. These findings suggest that learning and using rhythm-based music and movement interventions are promising for lowering stress in caregivers. The impact of the intervention with families at risk due to stress-related environmental factors should be further investigated. In addition, observing social emotional behaviors and stress hormone levels of the infant is suggested.

scholarly journals Medical Schools' Industry Interaction Policies Not Associated With Trainees' Self-Reported Behavior as Residents: Results of a National Survey

2015 ◽  
Vol 7 (4) ◽  
pp. 595-602 ◽  
Author(s):  
James S. Yeh ◽  
Kirsten E. Austad ◽  
Jessica M. Franklin ◽  
Susan Chimonas ◽  
Eric G. Campbell ◽  
...  
Keyword(s):  
Medical School ◽  
American Medical ◽  
Medical Schools ◽  
Brand Name ◽  
School Policies ◽  
Student Interactions ◽  
Drug Products ◽  
Interaction Behaviors ◽  
American Medical Student Association ◽  
Pharmaceutical Representatives

ABSTRACT Background Medical students attending schools with policies limiting industry/student interactions report fewer relationships with pharmaceutical representatives. Objective To investigate whether associations between students' medical school policies and their more limited industry interaction behaviors persist into residency. Methods We randomly sampled 1800 third-year residents who graduated from 120 allopathic US-based medical schools, using the American Medical Association Physician Masterfile. We surveyed them in 2011 to determine self-reported behavior and preferences for brand-name prescriptions, and we calculated the strength of their medical schools' industry interaction policies using the 2008 American Medical Student Association and Institute on Medicine as a Profession databases. We used logistic regression to estimate the association between strength of school policies and residents' behaviors with adjustments for class size, postresidency career plan, and concern about medical school debt. Results We achieved a 44% survey response rate (n = 739). Residents who graduated from schools with restrictive policies were no more or less likely to accept industry gifts or industry-sponsored meals, speak with marketing representative about drug products, attend industry-sponsored lectures, or prefer brand-name medications than residents who graduated from schools with less restrictive policies. Residents who correctly answered evidence-based prescription questions were about 30% less likely to have attended industry-sponsored lectures (OR = 0.72, 95% CI 0.56–0.98). Conclusions Any effect that medical school industry interaction policies had on insulating students from pharmaceutical marketing did not persist in the behavior of residents in our sample. This suggests that residency training environments are important in influencing behavior.

scholarly journals Recommending Mobile Microblog Users via a Tensor Factorization Based on User Cluster Approach

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Xiangwen Liao ◽  
Lingying Zhang ◽  
Jingjing Wei ◽  
Dingda Yang ◽  
Guolong Chen
Keyword(s):  
Network Centrality ◽  
Network Clustering ◽  
Tensor Factorization ◽  
Latent Factors ◽  
Cp Decomposition ◽  
Temporal Features ◽  
User Influence ◽  
Proposed Model ◽  
The Mean ◽  
Content Similarity

User influence is a very important factor for microblog user recommendation in mobile social network. However, most existing user influence analysis works ignore user’s temporal features and fail to filter the marketing users with low influence, which limits the performance of recommendation methods. In this paper, a Tensor Factorization based User Cluster (TFUC) model is proposed. We firstly identify latent influential users by neural network clustering. Then, we construct a features tensor according to latent influential user’s opinion, activity, and network centrality information. Furthermore, user influences are predicted by the latent factors resulting from the temporal restrained CP decomposition. Finally, we recommend microblog users considering both user influence and content similarity. Our experimental results show that the proposed model significantly improves recommendation performance. Meanwhile, the mean average precision of TFUC outperforms the baselines with 3.4% at least.

Sign in / Sign up

Export Citation Format

Share Document