Learning Geo-Social User Topical Profiles with Bayesian Hierarchical User Factorization

Lu, Haokai; Niu, Wei; Caverlee, James

doi:10.1145/3209978.3210044

Cited by 3 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Let us suppose that H has the Helly property, and we want to state something similar for H′. We prove a conjecture of C, Berge and two negative results [32,33]. Commonly discussed words in all the locations might not produce the correct location of the tweet.…”

Section: Helly Property In Hypergraphmentioning

confidence: 84%

Epidemic zone of COVID-19 from social media using hypergraph with weighting factor (HWF)

Pradeepa

Manjula

2021

J Supercomput

View full text Add to dashboard Cite

Online social network is one of the most prominent media that holds information about society's epidemic problem. Due to privacy reasons, most of the users will not disclose their location. Detecting the location of the tweet users is required to track the geographic location of the spreading diseases. This work aims to detect the spreading location of the COVID-19 disease from the Twitter users and content discussed in the tweet. COVID-19 is a disease caused by the "novel coronavirus." About 80% of confirmed cases recover from the disease. However, one out of every six people who get COVID-19 can become seriously ill, stated by the World health organization. Inferring the user location for identifying the spreading location for the disease is a very challenging task. This paper proposes a new technique based on a hypergraph model to detect the Twitter user's locations based on the spreading disease. This model uses hypergraph with weighting factor technique to infer the spreading disease's spatial location. The accuracy of prediction can be improved when a massive volume of streaming data is analyzed. The Helly property of the hypergraph was applied to discard less potential words from the text analysis, which claims this work of unique nature. A weighting factor was introduced to calculate the score of each location for a particular user. The location of each user is predicted based on the one that possesses the highest weighting factor. The proposed framework has been evaluated and tested for various measures like precision, recall and F-measure. The promising results obtained have substantiated the claim for this work compared to the state-of-the-art methodologies.

show abstract

Section: Helly Property In Hypergraphmentioning

confidence: 84%

Epidemic zone of COVID-19 from social media using hypergraph with weighting factor (HWF)

Pradeepa

Manjula

2021

J Supercomput

View full text Add to dashboard Cite

show abstract

“…Hierarchical structures on the latent variables have been explored (Ranganath et al, 2015;Liang et al, 2018). Other works have proposed to use additional information in the model to perform hybrid CF approaches (Gopalan et al, 2014;Lu et al, 2018;Salah and Lauw, 2018).…”

Section: Introductionmentioning

confidence: 99%

Recommendation from Raw Data with Adaptive Compound Poisson Factorization

Gouvert¹,

Oberlin²,

Févotte³

2019

Preprint

View full text Add to dashboard Cite

Count data are often used in recommender systems: they are widespread (song play counts, product purchases, clicks on web pages) and can reveal user preference without any explicit rating from the user. Such data are known to be sparse, over-dispersed and bursty, which makes their direct use in recommender systems challenging, often leading to pre-processing steps such as binarization. The aim of this paper is to build recommender systems from these raw data, by means of the recently proposed compound Poisson Factorization (cPF). The paper contributions are three-fold: we present a unified framework for discrete data (dcPF), leading to an adaptive and scalable algorithm; we show that our framework achieves a trade-off between Poisson Factorization (PF) applied to raw and binarized data; we study four specific instances that are relevant to recommendation and exhibit new links with combinatorics. Experiments with three different datasets show that dcPF is able to effectively adjust to over-dispersion, leading to better recommendation scores when compared with PF on either raw or binarized data.

show abstract

Deep Potential Geo-Social Relationship Mining for Point-of-Interest Recommendation

et al. 2019

View full text Add to dashboard Cite

Learning Geo-Social User Topical Profiles with Bayesian Hierarchical User Factorization

Cited by 3 publications

References 33 publications

Epidemic zone of COVID-19 from social media using hypergraph with weighting factor (HWF)

Epidemic zone of COVID-19 from social media using hypergraph with weighting factor (HWF)

Recommendation from Raw Data with Adaptive Compound Poisson Factorization

Deep Potential Geo-Social Relationship Mining for Point-of-Interest Recommendation

Contact Info

Product

Resources

About