scholarly journals Identifying Human Daily Activity Types with Time-Aware Interactions

2020 ◽  
Vol 10 (24) ◽  
pp. 8922
Author(s):  
Renyao Chen ◽  
Hong Yao ◽  
Runjia Li ◽  
Xiaojun Kang ◽  
Shengwen Li ◽  
...  
Keyword(s):  
Social Media ◽  
Human Activity ◽  
Model Performance ◽  
Heterogeneous Data ◽  
Accurate Identification ◽  
Convolutional Network ◽  
Proposed Model ◽  
Crowdsourced Data ◽  
Activity Types ◽  
Media Data

Human activities embedded in crowdsourced data, such as social media trajectory, represent individual daily styles and patterns, which are valuable in many applications. However, the accurate identification of human activity types (HATs) from social media is challenging, possibly because interactions between posts and users at different time are overlooked. To fill this gap, we propose a novel model that introduces the interactions hidden in social media and synthesizes Graph Convolutional Network (GCN) for identifying HAT. The model first characterizes interactions among words, posts, dates, and users, and then derives a Time Gated Human Activity Graph Convolutional Network (TG-HAGCN) to predict the HATs of social media trajectory. To examine the proposed model performance, we built a new dataset including interactions between post content, post time, and users from the open Yelp dataset. Experimental results show that exploiting interactions hidden in social media to recognize HATs achieves state-of-the-art performance with high accuracy. The study indicates that interactions among social media promotes ability of machine learning on social media data mining and intelligent applications, and offers a reference solution for how to fuse multi-type heterogeneous data in social media.

scholarly journals Participatory Social Sensor: A Framework to Social Media Data Acquisition and Analysis

2019 ◽  
Author(s):  
Igor Araujo ◽  
Paulo Henrique Lopes Rettore ◽  
João Guilherme Maia de Menezes
Keyword(s):  
Social Media ◽  
Data Acquisition ◽  
Visual Analysis ◽  
Social Behaviors ◽  
Data Access ◽  
Heterogeneous Data ◽  
Social Media Data ◽  
Analysis Process ◽  
Media Data ◽  
Social Sensor

Nowadays, understanding urban mobility, transit, people viewpoint, and social behaviors has been the focus of many research and investments. However, data access is restricted to private companies and governments. In addition, the costs to create a sensor infrastructure on a given area is prohibitive. Then, using Location-Based Social Media (LBSM) may provide a new way to better comprehend the social behaviors, by the use of a users viewpoint. In this work, we propose the use of LBSM as participatory sensing, designing the Participatory Social Sensor (PSS), a friendly framework to social media data acquisition and analysis. We develop the Twitter data acquisition and analysis process, aiming to achieve the user application goals through a file setup,where the user specifies the spatial area, temporal interval, tags, and other parameters. As a result, the PSS shows a set of visual analysis which provides a context overview, allowing an easy way to researchers make-decision. A case study, Detection and Enrichment Service for Road Events Based on Heterogeneous Data Merger for VANETs, based on PSS framework was published in the current conference.

scholarly journals Recognizing Human Daily Activity Using Social Media Sensors and Deep Learning

2019 ◽  
Vol 16 (20) ◽  
pp. 3955 ◽  
Author(s):  
Junfang Gong ◽  
Runjia Li ◽  
Hong Yao ◽  
Xiaojun Kang ◽  
Shengwen Li
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Human Activity ◽  
Daily Activity ◽  
Low Cost ◽  
Contextual Information ◽  
Learning Sequence ◽  
Proposed Model ◽  
Application Fields ◽  
Access Data

The human daily activity category represents individual lifestyle and pattern, such as sports and shopping, which reflect personal habits, lifestyle, and preferences and are of great value for human health and many other application fields. Currently, compared to questionnaires, social media as a sensor provides low-cost and easy-to-access data sources, providing new opportunities for obtaining human daily activity category data. However, there are still some challenges to accurately recognizing posts because existing studies ignore contextual information or word order in posts and remain unsatisfactory for capturing the activity semantics of words. To address this problem, we propose a general model for recognizing the human activity category based on deep learning. This model not only describes how to extract a sequence of higher-level word phrase representations in posts based on the deep learning sequence model but also how to integrate temporal information and external knowledge to capture the activity semantics in posts. Considering that no benchmark dataset is available in such studies, we built a dataset that was used for training and evaluating the model. The experimental results show that the proposed model significantly improves the accuracy of recognizing the human activity category compared with traditional classification methods.

scholarly journals A Framework for Forecasting Outbreak of Infectious Diseases Based on Climate Variability and Social Media Content

2021 ◽  
Vol 9 (5) ◽  
pp. 118-124
Author(s):  
Juliet Johny ◽  
Linda Sara Mathew
Keyword(s):  
Social Media ◽  
Infectious Diseases ◽  
Disease Incidence ◽  
Disease Outbreaks ◽  
Media Content ◽  
Data Generation ◽  
Real Time Analysis ◽  
Weather Observations ◽  
Proposed Model ◽  
Media Data

The amount of data has risen significantly over the last few years, due to the popularity of some of the data generation sources like social media, electronic health records, sensors and online shopping sites. Analyzing, processing and storing this data is very prominent since it helps to uncover hidden patterns and unknown correlations. A big data analysis and prediction System is proposed in this context, which combines weather observations, health data and social media content in order to forecast the outbreaks of infectious diseases in a locality. Finding information about the determinants of disease outbreaks are required to reduce its effects on populations. An In-mapper combiner based MapReduce algorithm is used to calculate the mean of daily measurements of various climate parameters like temperature, atmospheric pressure, relative humidity, solar and wind. The climatic parameter that may leads to the outbreak of a disease is identified by finding the correlation between the parameters and disease incidence count. To evaluate how user’s tweeting patterns and sentiments matched with the outbreak of diseases, all tweets containing keywords related to diseases are collected using twitter streaming APIs and are analyzed and processed using Spark framework. The performance of proposed model is improved due to the presence of tweet processing. This indicates that the real-time analysis of social media data can provide more effective result rather than working on the historical data.

scholarly journals The Graph-based Mutual Attentive Network for Automatic Diagnosis

2020 ◽  
Author(s):  
Quan Yuan ◽  
Jun Chen ◽  
Chao Lu ◽  
Haifeng Huang
Keyword(s):  
Sequence Learning ◽  
Structural Information ◽  
Model Performance ◽  
High Standard ◽  
Health Care Facilities ◽  
Diagnostic Process ◽  
Convolutional Network ◽  
Automatic Diagnosis ◽  
Proposed Model ◽  
Complex Structural

The automatic diagnosis has been suffering from the problem of inadequate reliable corpus to train a trustworthy predictive model. Besides, most of the previous deep learning based diagnosis models adopt the sequence learning techniques (CNN or RNN), which is difficult to extract the complex structural information, e.g. graph structure, between the critical medical entities. In this paper, we propose to build the diagnosis model based on the high-standard EMR documents from real hospitals to improve the accuracy and the credibility of the resulting model. Meanwhile, we introduce the Graph Convolutional Network into the model that alleviates the sparse feature problem and facilitates the extraction of structural information for diagnosis. Moreover, we propose the mutual attentive network to enhance the representation of inputs towards the better model performance. The evaluation conducted on the real EMR documents demonstrates that the proposed model is more accurate compared to the previous sequence learning based diagnosis models. The proposed model has been integrated into the information systems in over hundreds of primary health care facilities in China to assist physicians in the diagnostic process.

scholarly journals Using Machine Learning to Detect Events on the Basis of Bengali and Banglish Facebook Posts

Electronics ◽  
2021 ◽  
Vol 10 (19) ◽  
pp. 2367
Author(s):  
Noyon Dey ◽  
Md. Sazzadur Rahman ◽  
Motahara Sabah Mredula ◽  
A. S. M. Sanwar Hosen ◽  
In-Ho Ra
Keyword(s):  
Social Media ◽  
Detection System ◽  
Classification Model ◽  
Support Vector ◽  
Proposed Model ◽  
Prime Concern ◽  
Use Of Social Media ◽  
Bengali Language ◽  
Language Detection ◽  
Media Data

In modern times, ensuring social security has become the prime concern for security administrators. The widespread and recurrent use of social media sites is creating a huge risk for the lives of the general people, as these sites are frequently becoming potential sources of the organization of various types of immoral events. For protecting society from these dangers, a prior detection system which can effectively detect events by analyzing these social media data is essential. However, automating the process of event detection has been difficult, as existing processes must account for diverse writing styles, languages, dialects, post lengths, and et cetera. To overcome these difficulties, we developed an effective model for detecting events, which, for our purposes, were classified as either protesting, celebrating, religious, or neutral, using Bengali and Banglish Facebook posts. At first, the collected posts’ text were processed for language detection, and then, detected posts were pre-processed using stopwords removal and tokenization. Features were then extracted from these pre-processed texts using three sub-processes: filtering, phrase matching of specific events, and sentiment analysis. The collected features were ultimately used to train our Bernoulli Naive Bayes classification model, which was capable of detecting events with 90.41% accuracy (for Bengali-language posts) and 70% (for the Banglish-form posts). For evaluating the effectiveness of our proposed model more precisely, we compared it with two other classifiers: Support Vector Machine and Decision Tree.

scholarly journals USING CROWDSOURCED DATA (TWITTER & FACEBOOK) TO DELINEATE THE ORIGIN AND DESTINATION OF COMMUTERS OF THE GAUTRAIN PUBLIC TRANSIT SYSTEM IN SOUTH AFRICA

2016 ◽  
Vol III-2 ◽  
pp. 143-150 ◽  
Author(s):  
T. Moyo ◽  
W. Musakwa
Keyword(s):  
Social Media ◽  
Prediction Models ◽  
Transit System ◽  
Social Media Data ◽  
Points Of Interest ◽  
Crowdsourced Data ◽  
Data Source ◽  
Media Data ◽  
Inform Decision Making ◽  
Concentration Levels

The study of commuters’ origins and destinations (O_D) promises to assist transportation planners with prediction models to inform decision making. Conventionally O_D surveys are undertaken through travel surveys and traffic counts, however data collection for these surveys has historically proven to be time consuming and having a strain on human resources, thus a need for an alternative data source arises. This study combines the use social media data and geographic information systems in the creation of a model for origin and destination surveys. The model tests the potential of using big data from Echo echo software which contains Twitter and Facebook data obtained from social media users in Gauteng. This data contains geo-location and it is used to determine origin and destination as well as concentration levels of Gautrain commuters. A kriging analysis was performed on the data to determine the O-D and concentration levels of Gautrain users. The results reveal the concentration of Gautrain commuters at various points of interest that is where they work, live or socialise. The results from the study highlight which nodes attract the most commuters and also possible locations for the expansion for Gautrain. Lastly, the study also highlights some weakness of crowdsourced data for informing transportation planning.

scholarly journals BESOCIAL: A Sustainable Knowledge Graph-Based Workflow for Social Media Archiving

2021 ◽  
Author(s):  
Sven Lieber ◽  
Dylan Van Assche ◽  
Sally Chambers ◽  
Fien Messens ◽  
Friedel Geeraert ◽  
...  
Keyword(s):  
Social Media ◽  
Open Source ◽  
Public Discourse ◽  
Heterogeneous Data ◽  
Knowledge Graph ◽  
Social Media Data ◽  
Heterogeneous Data Sources ◽  
Metadata Standards ◽  
Data Stewardship ◽  
Media Data

Social media as infrastructure for public discourse provide valuable information that needs to be preserved. Several tools for social media harvesting exist, but still only fragmented workflows may be formed with different combinations of such tools. On top of that, social media data but also preservation-related metadata standards are heterogeneous, resulting in a costly manual process. In the framework of BESOCIAL at the Royal Library of Belgium (KBR), we develop a sustainable social media archiving workflow that integrates heterogeneous data sources in a Europeana and PREMIS-based data model to describe data preserved by open source tools. This allows data stewardship on a uniform representation and we generate metadata records automatically via queries. In this paper, we present a comparison of social media harvesting tools and our Knowledge Graph-based solution which reuses off-the-shelf open source tools to harvest social media and automatically generate preservation-related metadata records. We validate our solution by generating Encoded Archival Description (EAD) and bibliographic MARC records for preservation of harvested social media collections from Twitter collected at KBR. Other archiving institutions can build upon our solution and customize it to their own social media archiving policies.

scholarly journals A Density-based Nonparametric Model for Online Event Discovery from the Social Media Data

2017 ◽  
Author(s):  
Jinjin Guo ◽  
Zhiguo Gong
Keyword(s):  
Social Media ◽  
Dirichlet Process ◽  
Sequential Monte Carlo ◽  
Temporal Dynamics ◽  
Nonparametric Model ◽  
Parameter Inference ◽  
Social Media Data ◽  
Proposed Model ◽  
The Social ◽  
Media Data

In this paper, we propose a novel online event discovery model DP-density to capture various events from the social media data. The proposed model can flexibly accommodate the incremental arriving of the social documents in an online manner by leveraging Dirichlet Process, and a density based technique is exploited to deduce the temporal dynamics of events. The spatial patterns of events are also incorporated in the model by a mixture of Gaussians. To remove the bias caused by the streaming process of the documents, Sequential Monte Carlo is used for the parameter inference. Our extensive experiments over two different real datasets show that the proposed model is capable to extract interpretable events effectively in terms of perplexity and coherence.

Sign in / Sign up

Export Citation Format

Share Document