A Recommender Model Based on Strong and Weak Social Ties: A Long-tail Distribution Perspective

2021 ◽  
pp. 115483
Author(s):  
Wei-jun He ◽  
Dan-xiang Ai ◽  
ChienHsing Wu
Keyword(s):  
Social Ties ◽  
Long Tail ◽  
Model Based ◽  
Tail Distribution

Automatic Generation of an Aspect and Domain Sensitive Sentiment Lexicon

2014 ◽  
Vol 23 (04) ◽  
pp. 1460019
Author(s):  
Hsiang Hui Lek ◽  
Danny Chiang Choon Poo
Keyword(s):  
Sentiment Analysis ◽  
State Of The Art ◽  
Automatic Generation ◽  
Research Community ◽  
Automatic Method ◽  
Long Tail ◽  
Tail Distribution ◽  
Sentiment Lexicon ◽  
Fully Automatic ◽  
Distribution Behavior

Sentiment lexicon plays an important role in determining the polarity of words and proves to be an important component in sentiment analysis applications. Most of these sentiment lexicons assign a fixed polarity to each word. However, it has been noted that the polarity of words depends on how they are used and so these lexicons are unable to accurately classify the polarity of the sentiments. By considering the aspect and domain of a word will allow us to more accurately classify sentiments. This paper presents a fully automatic method to build an aspect and domain sensitive sentiment lexicon which assigns a polarity to a word depending on both the aspect and the domain. The experimental results show that our lexicon significantly outperforms other commonly used sentiment lexicons / state-of-the-art approaches. To the best of our knowledge, such a lexicon is not publicly available. As such, we also make this lexicon publicly available as we believe it will benefit the research community. In addition, we observe the long tail distribution behavior of product aspects and propose the possibility of aspect ranking by comparing the number of domains and number of sentiment words present for an aspect.

scholarly journals Finding College Student Social Networks by Mining the Records of Student ID Transactions

Symmetry ◽  
2019 ◽  
Vol 11 (3) ◽  
pp. 307 ◽  
Author(s):  
Jing-Ya Xu ◽  
Tao Liu ◽  
Lin-Tao Yang ◽  
Mark Davison ◽  
Shou-Yin Liu
Keyword(s):  
College Students ◽  
Social Networks ◽  
Association Rules ◽  
Social Ties ◽  
Time Window ◽  
Adaptive Method ◽  
Model Based ◽  
Student Management ◽  
Window Method ◽  
The Social

Information about college students’ social networks plays a pivotal role in college students’ mental health monitoring and student management. While there have been many studies to infer social networks by data mining, the mining of college students’ social networks lacks consideration of homophily. College students’ social behaviors show significant homophily in the aspect of major and grade. Consequently, the inferred inter-major and inter-grade social ties will be erroneously omitted without considering such an effect. In this work, we aimed to increase the fidelity of the extracted networks by alleviating the homophily effect. To achieve this goal, we propose a method that combines the sliding time-window method with the hierarchical encounter model based on association rules. Specifically, we first calculated the counts of spatial–temporal co-occurrences of each student pair. The co-occurrences were acquired by the sliding time-window method, which takes advantage of the symmetry of the social ties. We then applied the hierarchical encounter model based on association rules to extract social networks by layer. Furthermore, we propose an adaptive method to set co-occurrence thresholds. Results suggested that our model infers the social networks of students with better fidelity, with the proportion of extracted inter-major social ties in entire social ties increasing from 0.89% to 5.45% and the proportion of inter-grade social ties rising from 0.92% to 4.65%.

Extracting Core Users Based on Features of Users and Their Relationships in Recommender Systems

2017 ◽  
Vol 14 (2) ◽  
pp. 1-23
Author(s):  
Li Kuang ◽  
Gaofeng Cao ◽  
Liang Chen
Keyword(s):  
Recommender System ◽  
Degree Distribution ◽  
Information Overload ◽  
Extraction Methods ◽  
Long Tail ◽  
Trust Relationships ◽  
Tail Distribution ◽  
Trust Degree ◽  
Interest Similarity ◽  
New Algorithms

As an effective way to solve information overload, recommender system has drawn attention of scholars from various fields. However, existing works mainly focus on improving the accuracy of recommendation by designing new algorithms, while the different importance of individual users has not been well addressed. In this paper, the authors propose new approaches to identifying core users based on trust relationships and interest similarity between users, and the popular degree, trust influence and resource of individual users. First, the trust degree and interest similarity between all user pairs, as well as the three attributes of individuals are calculated. Second, a global core user set is constructed based on three strategies, which are frequency-based, rank-based, and fusion-sorting-based. Finally, the authors compare their proposed methods with other existing methods from accuracy, novelty, long-tail distribution and user degree distribution. Experiments show the effectiveness of the authors' core user extraction methods.

Pairwise deep learning to rank for top-N recommendation

2021 ◽  
pp. 1-12
Author(s):  
Wang Zhou ◽  
Yujun Yang ◽  
Yajun Du ◽  
Amin Ul Haq
Keyword(s):  
Neural Network ◽  
High Performance ◽  
Learning To Rank ◽  
Pairwise Comparison ◽  
Long Tail ◽  
Pairwise Learning ◽  
Tail Distribution ◽  
Computational Capability ◽  
Real World Datasets ◽  
Ranking Loss

Recent researches indicate that pairwise learning to rank methods could achieve high performance in dealing with data sparsity and long tail distribution in item recommendation, although suffering from problems such as high computational complexity and insufficient samples, which may cause low convergence and inaccuracy. To further improve the performance in computational capability and recommendation accuracy, in this article, a novel deep neural network based recommender architecture referred to as PDLR is proposed, in which the item corpus will be partitioned into two collections of positive instances and negative items respectively, and pairwise comparison will be performed between the positive instances and negative samples to learn the preference degree for each user. With the powerful capability of neural network, PDLR could capture rich interactions between each user and items as well as the intricate relations between items. As a result, PDLR could minimize the ranking loss, and achieve significant improvement in ranking accuracy. In practice, experimental results over four real world datasets also demonstrate the superiority of PDLR in contrast to state-of-the-art recommender approaches, in terms of Rec@N, Prec@N, AUC and NDCG@N.

scholarly journals ANALYZING THE VELOCITY OF URBAN DYNAMIC OVER NORTHEASTERN CHINA USING DMSP-OLS NIGHT-TIME LIGHTS

2017 ◽  
Vol XLII-2/W7 ◽  
pp. 1477-1480
Author(s):  
Y. Zhou
Keyword(s):  
Northeastern China ◽  
Night Time ◽  
Velocity Change ◽  
Long Tail ◽  
Defense Meteorological Satellite Program ◽  
Tail Distribution ◽  
Anthropogenic Development ◽  
Urban Dynamic ◽  
Good Proxy ◽  
Meteorological Satellite

Stable night-time lights (NTL) data from the Defense Meteorological Satellite Program Operational Line-scan System (DMSPOLS) can serve as a good proxy for anthropogenic development. Here DMSP-OLS NTL data was used to detect the urban development status in northeastern China. The spatial and temporal gradients are combined to depict the velocity of urban expanding process. This velocity index represents the instantaneous local velocity along the Earth’s surface needed to maintain constant NTL condition, and has a mean of 0.36 km/yr for northeastern China. The velocity change of NTL is lower in the urban center and its near regions, and the suburbs show a relatively high value. The connecting zones between satellite cities and metropolis have also a rapid rate of NTL evolution. The dynamic process of urbanization over the study area is mainly in a manner of spreading from urban cores to edges. The rank size of the velocity for the prefectures is analyzed and a long tail distribution is found. The velocity index can provide insights for the future pattern of urban sprawl.

scholarly journals Nonlinear Stochastic Equation within an Itô Prescription for Modelling of Financial Market

Entropy ◽  
2019 ◽  
Vol 21 (5) ◽  
pp. 530 ◽  
Author(s):  
Leonardo S. Lima
Keyword(s):  
Mathematical Model ◽  
Financial Markets ◽  
Financial Market ◽  
Stochastic Models ◽  
Stochastic Equation ◽  
Planck Equation ◽  
Cumulative Probability ◽  
Long Tail ◽  
Inverse Power Law ◽  
Tail Distribution

The stochastic nonlinear model based on Itô diffusion is proposed as a mathematical model for price dynamics of financial markets. We study this model with relation to concrete stylised facts about financial markets. We investigate the behavior of the long tail distribution of the volatilities and verify the inverse power law behavior which is obeyed for some financial markets. Furthermore, we obtain the behavior of the long range memory and obtain that it follows to a distinct behavior of other stochastic models that are used as models for the finances. Furthermore, we have made an analysis by using Fokker–Planck equation independent on time with the aim of obtaining the cumulative probability distribution of volatilities P ( g ) , however, the probability density found does not exhibit the cubic inverse law.

Sign in / Sign up

Export Citation Format

Share Document