Demographic Attribute Inference from Social Multimedia Behaviors: A Cross-OSN Approach

Xiang, Liancheng; Sang, Jitao; Xu, Changsheng

doi:10.1007/978-3-319-51811-4_42

Cited by 10 publications

(21 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3.2 Studies developing methods for gender and age prediction 3.2.1 Gender 44 studies developed ad-hoc methods to predict the Twitter user's gender. Of these, 32 predicted only gender 28,29,31,33,36,37,47,48,50,51,54,55,58,60,61,64,65,68,71,72,75,81,[83][84][85][86]90,92,94,96,100,101 and gender was predicted along with the user's age in 12 34,44,49,59,62,66,80,80,87,89,91,95 .…”

Section: Characteristics Of Included Studiesmentioning

confidence: 99%

“…These components were used either for the purpose of manually or semi-automatically validating the gender of a user or for the purpose of computing features describing the user to train a classifier (SI Table S5). Despite data limitations from the Twitter API, it was the main source of data collection, with 18 studies 28,30,31,33,48,50,51,55,58,62,68,71,[85][86][87]95,96,100 collecting data either as a random sample from the Twitter Streaming API or based on keywords or geographic location from the Twitter Search API. One study 61 collected data using a scraping tool, three 59,91,92 used a random sample from a collection of 10% of tweets from 2014-2017 or the Twitter archive, and one did not specify its data source 44 .…”

Section: Datasetsmentioning

confidence: 99%

“…The studies that created a labeled dataset (SI Table S6) to train and test, or to validate the performance of the system determined the gender of the users using multiple components of their Twitter accounts (SI Table S5). Eleven studies labeled the data through manual annotation where the annotators determined the gender using profile pictures 31,33 , user names 50 , profiles 68 , or a combination of these 55,61,71,85,87,89,95 . There were 11 studies that automatically, or (semi)-automatically, labeled their data sets through the detection of selfreports or gender identifying terms (e.g., mother, son, uncle, etc.)…”

Section: Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

Scoping Review of Methods and Annotated Datasets Used to Predict Gender and Age of Twitter Users

O’Connor

Golder

Weissenbacher

et al. 2022

Preprint

View full text Add to dashboard Cite

Real World Data (RWD) has been identified as a key information source in health and social science research. An important, and readily available source of RWD is social media. Identifying the gender and age of the authors of social media posts is necessary for assessing the representativeness of the sample by these key demographics and enables researchers to study subgroups and disparities. However, deciphering the age and gender of social media users can be challenging. We present a scoping review of the literature and summarize the automated methods used to predict age and gender of Twitter users. We used a systematic search method to identify relevant literature, of which 74 met our inclusion criteria. We found that although methods to extract age and gender evolved over time to utilize deep neural networks, many still relied on more traditional machine learning methods. Gender prediction has achieved higher reported performance, while prediction of age performance lags, particularly for more granular age groups. However, the heterogeneous nature of the studies and the lack of consistent performance measures made it impossible to quantitively synthesize results. We found evidence that data bias is a prevalent problem and discuss suggestions to minimize it for future studies.

show abstract

Section: Characteristics Of Included Studiesmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Scoping Review of Methods and Annotated Datasets Used to Predict Gender and Age of Twitter Users

O’Connor

Golder

Weissenbacher

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…L Xiang et al used dynamic social multimedia behaviour to infer stable demographic attributes and proposed a coupled projection matrix extraction (CPME) method [42] deduces a probability model to calculate the corresponding attributes of user-related topics according to the topics that users' likes and forward [43]. The study [44] proposed several models to infer user attributes based on social network interaction behaviour, including the interest pattern model (IPM), users' interest pattern model (UIPM) and community interest pattern model (CIPM).…”

Section: User Behavior-based Approachesmentioning

confidence: 99%

Privacy Inference Attack Against Users in Online Social Networks: A Literature Review

Piao

Cui

2021

IEEE Access

View full text Add to dashboard Cite

With the rapid development of social networks, users pay more and more attention to the protection of personal information. However, the transmission of users' personal information through social networks will inevitably lead to privacy leakage and make users attacked. A large amount of privacy information can be inferred from the content and social traces published by users, which leads to the rise of privacy inference technology for users in social networks. Social relationship inference and attribute inference are two basic attacks on users' privacy in social networks. This is the first systematic review of privacy inference attacks in social networks. The purpose of this retrospective study is to provide a global summary, summarizing the time trend of the topic, and show the evolution of the topic in the past 15 years. In addition, this paper discusses the trend and development of this topic and finally looks forward to future work. The contribution of our work is helpful for researchers to continue their research in this field.

show abstract

“…They compare the performance of three classifiers of Naive Bayes, Singular Value Machine (SVM) as well as Logistic Regression (LR), and find that LR shows the best performance. Xiang et al [5] infer user attributes using the spatio-temporal behavior of the same user across multiple OSNs. They represent each user using a combined feature vector converted from texts and images in Google+ and Twitter.…”

Section: A Behavior-based Inferencementioning

confidence: 99%

DeepAttr: Inferring Demographic Attributes via Social Network Embedding

et al. 2019

View full text Add to dashboard Cite

Online Social Networks (OSNs) (e.g., Facebook, Twitter, and Tecent QQ) are popular platforms for people to share information online. The providers of OSNs typically leverage demographic attributes of users in OSNs to perform business behaviors like personalized commodity recommendation, advertisement delivery, etc. Thus, understanding demographic attributes of users in OSNs is of great importance. However, some users refuse to reveal their demographic information due to privacy concerns. Therefore, inferring demographic attributes of users in OSNs with public information is an attractive topic for researchers. Most existing methods mainly focus on individual attribute inference without taking the relationship among attributes into account, which results in low precisions. In this paper, we propose a novel approach, called DeepAttr, to infer users' multiple attributes simultaneously. DeepAttr leverages existing network embedding algorithm to learn the social embedding for each user. Meanwhile, it encodes multiple attributes into structured attribute vectors which are treated as class labels. The core component of DeepAttr is a multi-layer fully connected deep neural network which captures complex nonlinear mapping between the users' social embeddings and the structured attribute vectors. Extensive experiments on a real-world dataset demonstrate that DeepAttr outperforms existing models in both single-attribute inference and multiple-attribute inference as to macro-Precision, macro-Recall, and macro-F1. INDEX TERMS Attribute inference, deep neural network, network embedding, online social network, structured attribute vector.

show abstract

Demographic Attribute Inference from Social Multimedia Behaviors: A Cross-OSN Approach

Cited by 10 publications

References 13 publications

Scoping Review of Methods and Annotated Datasets Used to Predict Gender and Age of Twitter Users

Scoping Review of Methods and Annotated Datasets Used to Predict Gender and Age of Twitter Users

Privacy Inference Attack Against Users in Online Social Networks: A Literature Review

DeepAttr: Inferring Demographic Attributes via Social Network Embedding

Contact Info

Product

Resources

About