Television by the numbers: The challenges of audience measurement in the age of Big Data

2017 ◽  
Vol 25 (1) ◽  
pp. 113-132 ◽  
Author(s):  
JP Kelly
Keyword(s):  
Social Media ◽  
Big Data ◽  
Real Time ◽  
Creative Industries ◽  
Data Sets ◽  
Audience Research ◽  
Television Industry ◽  
Real Time Analysis ◽  
Production Culture ◽  
Social Media Platforms

This article examines recent innovations in how television audiences are measured, paying particular attention to the industry's growing efforts to utilize the large bodies of data generated through social media platforms – a paradigm of research known as Big Data. Although Big Data is considered by many in the television industry as a more veracious model of audience research, this essay uses Boyd and Crawford's (2011) `Six Provocations of Big Data' to problematize and interrogate this prevailing industrial consensus. In doing so, this article explores both the affordances and the limitations of this emerging research paradigm – the latter having largely been ignored by those in the industry – and considers the consequences of these developments for the production culture of television more broadly. Although the full impact of the television industry's adoption of Big Data remains unclear, this article traces some preliminary connections between the introduction of these new measurement practices and the production culture of contemporary television. First, I demonstrate how the design of Big Data privileges real-time analysis, which, in turn, encourages increased investment in ‘live’ and/or ‘event’ television. Second, I argue that despite its potential to produce real-time insights, the scale of Big Data actually limits its utility in the context of the creative industries. Third, building on this discussion of the debatable value and applicability of Big Data, I describe how the introduction of social media metrics is further contributing to a ‘data divide’ in which access to these new information data sets is highly uneven, generally favouring institutions over individuals. Taken together, these three different but overlapping developments provide evidence that the introduction of Big Data is already having a notable effect on the television industry in a number of interesting and unexpected ways.

scholarly journals Classification Connection of Twitter Data using K-Means Clustering

2019 ◽  
Vol 8 (6S4) ◽  
pp. 14-22
Keyword(s):  
Social Media ◽  
Real Time ◽  
Clustering Methods ◽  
Time Analysis ◽  
Data Set ◽  
Dynamic Data ◽  
Real Time Analysis ◽  
Twitter Data ◽  
Social Media Platforms ◽  
Insight Into

The rise of social media platforms like Twitter and the increasing adoption by people in order to stay connected provide a large source of data to perform analysis based on the various trends, events and even various personalities. Such analysis also provides insight into a person’s likes and inclinations in real time independent of the data size. Several techniques have been created to retrieve such data however the most efficient technique is clustering. This paper provides an overview of the algorithms of the various clustering methods as well as looking at their efficiency in determining trending information. The clustered data may be further classified by topics for real time analysis on a large dynamic data set. In this paper, data classification is performed and analyzed for flaws followed by another classification on the same data set.

Facial Nerve EMG: Low-Tech Monitoring with a Stopwatch

2021 ◽  
Author(s):  
Julian Prell ◽  
Christian Scheller ◽  
Sebastian Simmermacher ◽  
Christian Strauss ◽  
Stefan Rampp
Keyword(s):  
Facial Nerve ◽  
Real Time ◽  
Random Order ◽  
Automated Analysis ◽  
Data Sets ◽  
Time Analysis ◽  
Frequency Pattern ◽  
Real Time Analysis ◽  
Offline Analysis ◽  
Automated Algorithms

Abstract Objective The quantity of A-trains, a high-frequency pattern of free-running facial nerve electromyography, is correlated with the risk for postoperative high-grade facial nerve paresis. This correlation has been confirmed by automated analysis with dedicated algorithms and by visual offline analysis but not by audiovisual real-time analysis. Methods An investigator was presented with 29 complete data sets measured during actual surgeries in real time and without breaks in a random order. Data were presented either strictly via loudspeaker (audio) or simultaneously by loudspeaker and computer screen (audiovisual). Visible and/or audible A-train activity was then quantified by the investigator with the computerized equivalent of a stopwatch. The same data were also analyzed with quantification of A-trains by automated algorithms. Results Automated (auto) traintime (TT), known to be a small, yet highly representative fraction of overall A-train activity, ranged from 0.01 to 10.86 s (median: 0.58 s). In contrast, audio-TT ranged from 0 to 1,357.44 s (median: 29.69 s), and audiovisual-TT ranged from 0 to 786.57 s (median: 46.19 s). All three modalities were correlated to each other in a highly significant way. Likewise, all three modalities correlated significantly with the extent of postoperative facial paresis. As a rule of thumb, patients with visible/audible A-train activity < 1 minute presented with a more favorable clinical outcome than patients with > 1 minute of A-train activity. Conclusion Detection and even quantification of A-trains is technically possible not only with intraoperative automated real-time calculation or postoperative visual offline analysis, but also with very basic monitoring equipment and real-time good quality audiovisual analysis. However, the investigator found audiovisual real-time-analysis to be very demanding; thus tools for automated quantification can be very helpful in this respect.

scholarly journals Measuring the Effectiveness of Adaptive Random Forest for Handling Concept Drift in Big Data Streams

Entropy ◽  
2021 ◽  
Vol 23 (7) ◽  
pp. 859
Author(s):  
Abdulaziz O. AlQabbany ◽  
Aqil M. Azmi
Keyword(s):  
Big Data ◽  
Random Forest ◽  
Real Time ◽  
Data Streams ◽  
Learning Algorithm ◽  
Concept Drift ◽  
The United States ◽  
Careful Consideration ◽  
Data Sets ◽  
Stream Data

We are living in the age of big data, a majority of which is stream data. The real-time processing of this data requires careful consideration from different perspectives. Concept drift is a change in the data’s underlying distribution, a significant issue, especially when learning from data streams. It requires learners to be adaptive to dynamic changes. Random forest is an ensemble approach that is widely used in classical non-streaming settings of machine learning applications. At the same time, the Adaptive Random Forest (ARF) is a stream learning algorithm that showed promising results in terms of its accuracy and ability to deal with various types of drift. The incoming instances’ continuity allows for their binomial distribution to be approximated to a Poisson(1) distribution. In this study, we propose a mechanism to increase such streaming algorithms’ efficiency by focusing on resampling. Our measure, resampling effectiveness (ρ), fuses the two most essential aspects in online learning; accuracy and execution time. We use six different synthetic data sets, each having a different type of drift, to empirically select the parameter λ of the Poisson distribution that yields the best value for ρ. By comparing the standard ARF with its tuned variations, we show that ARF performance can be enhanced by tackling this important aspect. Finally, we present three case studies from different contexts to test our proposed enhancement method and demonstrate its effectiveness in processing large data sets: (a) Amazon customer reviews (written in English), (b) hotel reviews (in Arabic), and (c) real-time aspect-based sentiment analysis of COVID-19-related tweets in the United States during April 2020. Results indicate that our proposed method of enhancement exhibited considerable improvement in most of the situations.

scholarly journals A GOOD LIFE? CRITICAL FEMINIST APPROACHES TO INFLUENCER ECOLOGIES

2020 ◽  
Author(s):  
Zoë Glatt ◽  
Sarah Banet-Weiser ◽  
Sophie Bishop ◽  
Francesca Sobande ◽  
Elizabeth Wissinger ◽  
...  
Keyword(s):  
Social Media ◽  
Cultural Production ◽  
Good Life ◽  
Social Economic ◽  
Creative Industries ◽  
The Good Life ◽  
Barriers To Entry ◽  
High Profile ◽  
Social Media Platforms

Social media platforms are widely lauded as bastions for entrepreneurial self-actualisation and creative autonomy, offering an answer to historically exclusive and hierarchical creative industries as routes to employability and success. Social media influencers are envied by audiences as having achieved ‘the good life’, one in which they are able to ‘do what they love’ for a living (Duffy 2017). Despite this ostensive accessibility and relatability, today’s high-profile influencer culture continues to be shaped by ‘preexisting gendered and racial scripts and their attendant grammars of exclusion’ as Sarah Banet-Weiser (2012) argued in the early days of socially mediated entrepreneurship (p. 89; see also Bishop, 2017). In Western contexts only a narrow subset of white, cis-gender, and heterosexual YouTubers, Instagrammers, TikTokers, and Twitch streamers tend to achieve visibility as social media star-creators, and celebratory discourses of diversity and fairness mask problematic structures that exclude marginalized identities from opportunities to attain success. A key aim of this panel is thus to draw attention to marginalized creator communities and subjectivities, including women, non-white, and queer creators, all of whom face higher barriers to entry and success. More broadly, by taking seriously both the practices and discourses of social media influencers, the panellists aim to challenge popular denigrations of influencers as vapid, frivolous, or eager to freeload. We locate such critiques in longstanding dismissals of feminized cultural production (Levine, 2013) and argue, instead, that we need to take seriously the role of influencers in various social, economic, and political configurations.

A Real-Time Log Analyzer Based on MongoDB

2014 ◽  
Vol 571-572 ◽  
pp. 497-501 ◽  
Author(s):  
Qi Lv ◽  
Wei Xie
Keyword(s):  
Real Time ◽  
Large Scale ◽  
Performance Comparison ◽  
Log Analysis ◽  
Data Sets ◽  
Time Data ◽  
Real Time Analysis ◽  
Large Scale Data ◽  
Implementation Approach ◽  
And Performance

Real-time log analysis on large scale data is important for applications. Specifically, real-time refers to UI latency within 100ms. Therefore, techniques which efficiently support real-time analysis over large log data sets are desired. MongoDB provides well query performance, aggregation frameworks, and distributed architecture which is suitable for real-time data query and massive log analysis. In this paper, a novel implementation approach for an event driven file log analyzer is presented, and performance comparison of query, scan and aggregation operations over MongoDB, HBase and MySQL is analyzed. Our experimental results show that HBase performs best balanced in all operations, while MongoDB provides less than 10ms query speed in some operations which is most suitable for real-time applications.

scholarly journals Detecting Damage Building Using Real-Time Crowdsourced Images And Transfer Learning

2021 ◽  
Author(s):  
Gaurav Chachra ◽  
Qingkai Kong ◽  
Jim Huang ◽  
Srujay Korlakunta ◽  
Jennifer Grannen ◽  
...  
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Real Time ◽  
Transfer Learning ◽  
Learning Model ◽  
Research Community ◽  
Rescue Work ◽  
The Public ◽  
Social Media Platforms ◽  
Deep Learning Model

Abstract After significant earthquakes, we can see images posted on social media platforms by individuals and media agencies owing to the mass usage of smartphones these days. These images can be utilized to provide information about the shaking damage in the earthquake region both to the public and research community, and potentially to guide rescue work. This paper presents an automated way to extract the damaged building images after earthquakes from social media platforms such as Twitter and thus identify the particular user posts containing such images. Using transfer learning and ~6500 manually labelled images, we trained a deep learning model to recognize images with damaged buildings in the scene. The trained model achieved good performance when tested on newly acquired images of earthquakes at different locations and ran in near real-time on Twitter feed after the 2020 M7.0 earthquake in Turkey. Furthermore, to better understand how the model makes decisions, we also implemented the Grad-CAM method to visualize the important locations on the images that facilitate the decision.

Remote Patient Monitoring for Healthcare

2019 ◽  
pp. 163-179 ◽  
Author(s):  
Andrew Stranieri ◽  
Venki Balasubramanian
Keyword(s):  
Real Time ◽  
Data Analytics ◽  
Patient Monitoring ◽  
Wearable Sensors ◽  
Data Sets ◽  
Remote Patient Monitoring ◽  
Data Mining Algorithms ◽  
Real Time Analysis ◽  
Huge Data ◽  
Remote Patient

Remote patient monitoring involves the collection of data from wearable sensors that typically requires analysis in real time. The real-time analysis of data streaming continuously to a server challenges data mining algorithms that have mostly been developed for static data residing in central repositories. Remote patient monitoring also generates huge data sets that present storage and management problems. Although virtual records of every health event throughout an individual's lifespan known as the electronic health record are rapidly emerging, few electronic records accommodate data from continuous remote patient monitoring. These factors combine to make data analytics with continuous patient data very challenging. In this chapter, benefits for data analytics inherent in the use of standards for clinical concepts for remote patient monitoring is presented. The openEHR standard that describes the way in which concepts are used in clinical practice is well suited to be adopted as the standard required to record meta-data about remote monitoring. The claim is advanced that this is likely to facilitate meaningful real time analyses with big remote patient monitoring data. The point is made by drawing on a case study involving the transmission of patient vital sign data collected from wearable sensors in an Indian hospital.

Real Time Analysis Based on Intelligent Applications of Big Data and IoT in Smart Health Care Systems

2020 ◽  
pp. 1839-1857
Author(s):  
Mamata Rath
Keyword(s):  
Health Care ◽  
Big Data ◽  
Data Analytics ◽  
Treatment Plan ◽  
Big Data Analytics ◽  
Data Sets ◽  
Care Services ◽  
Real Time Analysis ◽  
Health Care Applications ◽  
Care Systems

Currently, there is an expanding interest for additional medical data from patients about their healthcare choices and related decisions, and they further need investment in their basic health issues. Big data provides patients presumptuous data to help them settle on the best choice and align with their medicinal treatment plan. One of the very advanced concepts related to the synthesis of big data sets to reveal the hidden pattern in them is big data analytics. It involves demanding techniques to mine and extract relevant data that includes the actions of piercing a database, effectively mine the data, query and inspect the data and is committed to enhance the technical execution of various task segments. The capacity to synthesize a lot of data can enable an association to manage data that can influence the business. In this way, the primary goal of big data analytics is to help business relationships to have enhanced comprehension of data, and subsequently, settle on proficient and very much educated decisions. Big data analytics empowers data diggers and researchers to examine an extensive volume of data that may not be outfit utilizing customary apparatuses. Big data analytics require advances and statistical instruments that can change a lot of organized, unstructured, and semi-organized data into more reasonable data and metadata designed for explanatory procedures. There is tremendous positive potential concerning the application of big data in human health care services and many related major applications are still in their developmental stages. The deployment of big data in health service demonstrates enhancing health care results and controlling the expenses of common people due to treatment, as proven by some developing use cases. Keeping in view such powerful processing capacity of big data analytics in various technical fields of modern civilization related to health care, the current research article presents a comprehensive study and investigation on big data analytics and its application in multiple sectors of society with significance in health care applications.

Social Media Analytics

2022 ◽  
pp. 385-410
Author(s):  
Časlav Kalinić ◽  
Miroslav D. Vujičić
Keyword(s):  
Social Media ◽  
Big Data ◽  
Cultural Tourism ◽  
Social Media Analytics ◽  
Online Platforms ◽  
New Information ◽  
People Participation ◽  
Management And Development ◽  
Social Media Platforms ◽  
Tourism Destinations

The rise of social media allowed greater people participation online. Platforms such as Facebook, Twitter, Instagram, or TikTok enable visitors to share their thoughts, opinions, photos, locations. All those interactions create a vast amount of data. Social media analytics, as a way of application of big data, can provide excellent insights and create new information for stakeholders involved in the management and development of cultural tourism destinations. This chapter advocates for the employment of the big data concept through social media analytics that can contribute to the management of visitors in cultural tourism destinations. In this chapter, the authors highlight the principles of big data and review the most influential social media platforms – Facebook, Twitter, Instagram, and TikTok. On that basis, they disclose opportunities for the management and marketing of cultural tourism destinations.

Sign in / Sign up

Export Citation Format

Share Document