Over the last few years, much online volunteered geographic information (VGI) has emerged and been increasingly analyzed to understand places cities, as well human mobility activity. However, there are concerns about quality usability of such VGI. In this study, we demonstrate a complete process that comprises collection, unification, classification validation type VGI—online point-of-interest (POI) data—and develop methods utilize POI data estimate disaggregated land use (i.e., employment...

There is a growing consensus that online platforms have systematic influence on the democratic process. However, research beyond social media limited. In this paper, we report results of mixed-methods algorithm audit partisan audience bias and personalization within Google Search. Following Donald Trump's inauguration, recruited 187 participants to complete survey install browser extension enabled us collect Search Engine Results Pages (SERPs) from their computers. To quantify bias,...

Misinformation and fact-checking are opposite forces in the news environment: former creates inaccuracies to mislead people, while latter provides evidence rebut former. These articles often posted on social media attract user engagement form of comments. In this paper, we investigate linguistic (especially emotional topical) signals expressed comments presence misinformation fact-checking. We collect analyze a dataset 5,303 posts with 2,614,374 from Facebook, Twitter, YouTube, associate...

Academics, activists, and regulators are increasingly urging companies to develop deploy sociotechnical systems that fair unbiased. Achieving this goal, however, is complex: the developer must (1) deeply engage with social legal facets of "fairness" in a given context, (2) software concretizes these values, (3) undergo an independent algorithm audit ensure technical correctness accountability their algorithms. To date, there few examples have transparently undertaken all three steps.

Research typically presumes that people believe misinformation and propagate it through their social networks. Yet, a wide range of motivations for sharing might impact its spread, as well people’s belief it. By examining research on news information generally, specifically, we derive broaden current understandings the to include factors may some extent mitigate presumed dangers society. To illustrate utility our viewpoint report data from preliminary study dis/belief reactions shared media...

Urban geographers, planners, and economists have long been studying urban spatial structure to understand the development of cities. Statistical data mining techniques, as proposed in this paper, go a way improving our knowledge about human activities extracted from travel surveys. As today, most simulators not yet incorporated various types individuals by their daily activities. In work, we detect clusters activity patterns, integrated with usage space time, show that routines can be highly...

Purpose The purpose of paper is twofold. First, it provides a consolidated overview the existing literature on “big data” and second, presents current trends opens up various future directions for researchers who wish to explore contribute in this rapidly evolving field. Design/methodology/approach To achieve objective study, bibliographic network techniques citation co-citation analysis was adopted. This involved an assessment 57 articles published over period five years (2011-2015) ten...

Ridesharing services such as Uber and Lyft have become an important part of the Vehicle For Hire (VFH) market, which used to be dominated by taxis. Unfortunately, ridesharing are not required share data like taxi services, has made it challenging compare competitive dynamics these or assess their impact on cities. In this paper, we comprehensively Uber, Lyft, taxis with respect key market features (supply, demand, price, wait time) in San Francisco New York City. Based point pattern...

The text snippets presented in web search results provide users with a slice of page content that they can quickly scan to help inform their click decisions. However, little is known about how these are generated or relate user's query. Motivated by the growing body evidence suggesting engine rankings influence undecided voters, we conducted an algorithm audit political partisanship Google Search relative webpages extracted from. To accomplish this, constructed lexicon partisan cues measure...

The rapid development of information technology has brought significant transformations, including adopting large model as an innovative tool for data analysis and processing. This is increasingly permeating the field higher education, offering substantial opportunities educational innovation reform. study explores technology's current application, advantages, impacts on education methodology involves analyzing case studies its application in teaching, scientific research, management....

Understanding the knowledge‐diffusion networks of patent inventors can help governments and businesses effectively use their investment to stimulate commercial science technology development. Such inventor are usually large complex. This study proposes a multidimensional network analysis framework that utilizes E xponential R andom G raph M odels ( ERGM s) simultaneously model knowledge‐sharing knowledge‐transfer processes, examine interactions, evaluate impacts structures public funding on...

Urban transportation systems are multimodal, sociotechnical systems; however, while their multimodal aspect has received extensive attention in recent literature on multiplex networks, been largely neglected. We present the first study of an urban system using network analysis and validated Origin-Destination travel demand, with Riyadh's planned metro as a case study. develop methods for analyzing impact additional layers existing dynamics, show that demand structure plays key quantitative...

Autocomplete algorithms, by design, steer inquiry. When a user provides root input, such as search query, these algorithms dynamically retrieve, curate, and present list of related inputs, suggestions. Although ubiquitous in online platforms, lack research addressing the ephemerality their outputs opacity functioning raises concerns transparency accountability on where inquiry is steered. Here, we introduce recursive algorithm interrogation (RAI), breadth-first method for auditing...

Fact-checking, which investigates claims made in public to arrive at a verdict supported by evidence and logical reasoning, has long been significant form of journalism combat misinformation the news ecosystem. Most fact-checks share common structured information (called factors) such as claim, claimant, verdict. In recent years, emergence ClaimReview standard schema for annotating those factors within fact-checking articles led wide adoption features online platforms (e.g., Google, Bing)....

Purpose The authors empirically examined social capital factors affecting patients' support acquisition with the aim of providing guidance to patients seeking online. Design/methodology/approach used network analysis extract data about from online health communities and text mining identify forms informational emotional grounded in online, text-based communication. Moreover, employed a random coefficient model understand dynamic influence on both support. Findings results empirical analyses...

The proliferation of online misinformation has been raising increasing societal concerns about its potential consequences, e.g., polarizing the public and eroding trust in institutions. These consequences are framed under public's susceptibility to such — a narrative that needs further investigation quantification. To this end, our paper proposes an observational approach model measure expressed (dis)beliefs (mis)information by leveraging social media comments as proxy. We collect sample...

The current popular traffic classification methods based on feature engineering and machine learning are difficult to obtain suitable sets for multiple tasks. Besides, data privacy policies prohibit network operators from collecting sharing that might compromise user privacy. To address these challenges, we propose FedETC, a federated framework allows participants learn global classifiers, while keeping locally encrypted invisible other participants. In addition, FedETC adopts...

Although an increasing number of studies have attempted to understand how people interact with others in web-based health communities, focusing on understanding individuals' patterns information exchange and social support communities are still limited. In this paper, we discuss patients' interactions develop into networks based a network framework empirically validate the care community contexts.This study aims explore various identify factors that affect such patterns.Using analysis text...