Using Data Analytics to Create a Digital Strategy That Drives Engagement and Views on Social Media

2020 ◽  
Vol 9 (S1) ◽  
pp. S9-S12
Author(s):  
David Pierce ◽  
Geoffre Sherman
Keyword(s):  
Social Media ◽  
Digital Literacy ◽  
Large Data ◽  
Sport Marketing ◽  
Data Set ◽  
Content Creation ◽  
New Strategy ◽  
Sports Organization ◽  
Using Data ◽  
Creativity And Innovation

Students are placed into a consulting role with SPT, a sport marketing agency hired to help a sports organization create a new strategy for video content creation on social media. Students are provided a large data set in Tableau with analytics that hold the key to increasing the team’s engagement and views of videos on social media. Can your students find the insights in the data to drive a new video strategy for social media? Can they turn those insights into a creative content plan that will engage and win fans in the future? Students will have the opportunity to demonstrate creativity and innovation, data-based decision making, and digital literacy.

scholarly journals Analyzing social media data: A mixed-methods framework combining computational and qualitative text analysis

2019 ◽  
Author(s):  
Matthew Andreotta ◽  
Robertus Nugroho ◽  
Mark Hurlstone ◽  
Fabio Boschetti ◽  
Simon Farrell ◽  
...  
Keyword(s):  
Social Media ◽  
Qualitative Analysis ◽  
Data Science ◽  
Large Data ◽  
Extraction Process ◽  
Data Set ◽  
Diverse Range ◽  
Social Media Data ◽  
Qualitative Thematic Analysis ◽  
Media Data

To qualitative researchers, social media offers a novel opportunity to harvest a massive and diverse range of content, without the need for intrusive or intensive data collection procedures. However, performing a qualitative analysis across a massive social media data set is cumbersome and impractical. Instead, researchers often extract a subset of content to analyze, but a framework to facilitate this process is currently lacking. We present a four-phased framework for improving this extraction process, which blends the capacities of data science techniques to compress large data sets into smaller spaces, with the capabilities of qualitative analysis to address research questions. We demonstrate this framework by investigating the topics of Australian Twitter commentary on climate change, using quantitative (Non-Negative Matrix inter-joint Factorization; Topic Alignment) and qualitative (Thematic Analysis) techniques. Our approach is useful for researchers seeking to perform qualitative analyses of social media, or researchers wanting to supplement their quantitative work with a qualitative analysis of broader social context and meaning.

scholarly journals CROWD4EMS: A CROWDSOURCING PLATFORM FOR GATHERING AND GEOLOCATING SOCIAL MEDIA CONTENT IN DISASTER RESPONSE

2019 ◽  
Vol XLII-3/W8 ◽  
pp. 331-340
Author(s):  
A. Ravi Shankar ◽  
J. L. Fernandez-Marquez ◽  
B. Pernici ◽  
G. Scalia ◽  
M. R. Mondardini ◽  
...  
Keyword(s):  
Social Media ◽  
Disaster Response ◽  
Task Force ◽  
Media Content ◽  
Data Set ◽  
Emergency Responders ◽  
Social Media Networks ◽  
Combining Data ◽  
Automatic Methods ◽  
Using Data

<p><strong>Abstract.</strong> Increase in access to mobile phone devices and social media networks has changed the way people report and respond to disasters. Community-driven initiatives such as Stand By Task Force (SBTF) or GISCorps have shown great potential by crowdsourcing the acquisition, analysis, and geolocation of social media data for disaster responders. These initiatives face two main challenges: (1) most of social media content such as photos and videos are not geolocated, thus preventing the information to be used by emergency responders, and (2) they lack tools to manage volunteers contributions and aggregate them in order to ensure high quality and reliable results. This paper illustrates the use of a crowdsourcing platform that combines automatic methods for gathering information from social media and crowdsourcing techniques, in order to manage and aggregate volunteers contributions. High precision geolocation is achieved by combining data mining techniques for estimating the location of photos and videos from social media, and crowdsourcing for the validation and/or improvement of the estimated location. The evaluation of the proposed approach is carried out using data related to the Amatrice Earthquake in 2016, coming from Flickr, Twitter and Youtube. A common data set is analyzed and geolocated by both the volunteers using the proposed platform and a group of experts. Data quality and data reliability is assessed by comparing volunteers versus experts results. Final results are shown in a web map service providing a global view of the information social media provided about the Amatrice Earthquake event.</p>

scholarly journals Metal and metalloid sequestration in a constructed wetland system for treatment of landfill leachate during 2003-2012

2017 ◽  
Author(s):  
Sylvia Waara ◽  
Tatsiana Bandaruk
Keyword(s):  
Removal Efficiency ◽  
Constructed Wetland ◽  
Landfill Leachate ◽  
Large Data ◽  
Sediment Traps ◽  
Data Set ◽  
Metals And Metalloids ◽  
Study Results ◽  
Wetland System ◽  
Using Data

The treatment of landfill leachate in constructed wetland systems is a common practice in Europe. However, very few studies were made to evaluate their performance over a long period of time. A free surface constructed wetland system consisting of sediment traps followed by 10 ponds connected with overflows was built at Atleverket near Örebro, Sweden in 2001. It receives pre-treated leachate from the municipal landfill. As part of the wetland monitoring programme a large data set on the surface concentrations of 15 metals and 2 metalloids has been collected from different sampling sites within the wetland during the operation period. In this study, the data from inlet and outlet of the wetland were compiled and analysed. The aim of this paper is therefore to estimate the removal efficiency of metals and metalloids using data on concentrations and flow and investigate the effect of wetland age on removal pattern. The elements with the highest removal efficiency were Al, As, Ba, Ca, Cr, Cu, Fe, Mn, Pb, V and Zn ranging from 95% for Pb to 65 % for Ca. The elements with the lowest reduction were B, Co K, Mg, Ni and S ranging from Co 56 % to 40 % for S. It was found that the removal efficiency was not related to inlet concentrations of the elements as the elements with high and low inlet concentrations were found in both groups. Analysis of reduction pattern also revealed that the group with higher removal efficiency showed fairly constant outlet concentrations during the study period, while the elements with lower removal efficiency demonstrated variable outlet concentrations. No statistical difference in removal due to age of the wetland was found. The study results showed that the wetland system has high removal efficiency of metals and metalloids and the removal pattern is not affected by age of the wetland. The influence on reduction due to leachate characteristics, wetland design and retention time will be discussed.

scholarly journals The mass, metabolism and length explanation can simultaneously calculate an animal’s mass and metabolic rate from its characteristic length

2016 ◽  
Author(s):  
Charles C Frasier
Keyword(s):  
Metabolic Rate ◽  
Body Mass ◽  
Body Fat ◽  
Characteristic Length ◽  
Large Data ◽  
Data Set ◽  
Mass Data ◽  
Length Data ◽  
Using Data ◽  
The Impact

It is shown that the mass, metabolism and length explanation (MMLE) can simultaneously compute an animal’s body mass and BMR given its characteristic length using data for humans. MMLE was advanced in 1984 to explain the relationship between metabolic rate and body mass for birds and mammals. It was modernized in 2015 by explicitly treating dynamic similarity of mammals’ skeletal musculature and revising the treatment of BMR. Using two primary equations MMLE deterministically computes the absolute value of Basal Metabolic Rate (BMR) and body mass for individual animals as functions of an individual animal’s characteristic length and sturdiness factor. The characteristic length is a measureable skeletal length associated with an animal’s means of propulsion. The sturdiness factor expresses how sturdy or gracile an animal is. Eight other parameters occur in the equations that vary little among animals in the same phylogenetic group. A mass and length data set with 575 entries from the orders Rodentia, Chiroptera, Artiodactyla, Carnivora, Perissodactyla and Proboscidea and a BMR and mass data set with 436 entries from the orders Rodentia, Chiroptera, Artiodactyla and Carnivora were used to estimate values for the parameters occurring in the equations. With the estimated values MMLE can exactly compute every BMR and mass datum from the BMR and mass data set. Furthermore, MMLE can exactly compute every body mass datum from the mass and length data set. Since there is not a data set that simultaneously reports body mass, BMR and characteristic length for individual animals from the mammal orders that were analyzed it could not be determined whether or not MMLE could simultaneously compute both an animal’s BMR and body mass given its characteristic length. There are large data sets that report body mass, BMR and height for humans. A human’s characteristic length can be estimated from height. In this paper human data categorized by sex, age and body mass index (BMI) are used to show that MMLE can indeed simultaneously compute a human’s body mass and BMR given his or her characteristic length. The MMLE body mass equation is modified to explicitly address body fat because it appears that humans are fatter than other running/walking placental mammals. Differences in body fat seem to account for body mass and BMR sexual dimorphism among humans. The impact on BMR of the large and metabolically expensive human brain is addressed. Also mitochondria capability decline with age is addressed.

scholarly journals The mass, metabolism and length explanation can simultaneously calculate an animal’s mass and metabolic rate from its characteristic length

2016 ◽  
Author(s):  
Charles C Frasier
Keyword(s):  
Metabolic Rate ◽  
Body Mass ◽  
Body Fat ◽  
Characteristic Length ◽  
Large Data ◽  
Data Set ◽  
Mass Data ◽  
Length Data ◽  
Using Data ◽  
The Impact

It is shown that the mass, metabolism and length explanation (MMLE) can simultaneously compute an animal’s body mass and BMR given its characteristic length using data for humans. MMLE was advanced in 1984 to explain the relationship between metabolic rate and body mass for birds and mammals. It was modernized in 2015 by explicitly treating dynamic similarity of mammals’ skeletal musculature and revising the treatment of BMR. Using two primary equations MMLE deterministically computes the absolute value of Basal Metabolic Rate (BMR) and body mass for individual animals as functions of an individual animal’s characteristic length and sturdiness factor. The characteristic length is a measureable skeletal length associated with an animal’s means of propulsion. The sturdiness factor expresses how sturdy or gracile an animal is. Eight other parameters occur in the equations that vary little among animals in the same phylogenetic group. A mass and length data set with 575 entries from the orders Rodentia, Chiroptera, Artiodactyla, Carnivora, Perissodactyla and Proboscidea and a BMR and mass data set with 436 entries from the orders Rodentia, Chiroptera, Artiodactyla and Carnivora were used to estimate values for the parameters occurring in the equations. With the estimated values MMLE can exactly compute every BMR and mass datum from the BMR and mass data set. Furthermore, MMLE can exactly compute every body mass datum from the mass and length data set. Since there is not a data set that simultaneously reports body mass, BMR and characteristic length for individual animals from the mammal orders that were analyzed it could not be determined whether or not MMLE could simultaneously compute both an animal’s BMR and body mass given its characteristic length. There are large data sets that report body mass, BMR and height for humans. A human’s characteristic length can be estimated from height. In this paper human data categorized by sex, age and body mass index (BMI) are used to show that MMLE can indeed simultaneously compute a human’s body mass and BMR given his or her characteristic length. The MMLE body mass equation is modified to explicitly address body fat because it appears that humans are fatter than other running/walking placental mammals. Differences in body fat seem to account for body mass and BMR sexual dimorphism among humans. The impact on BMR of the large and metabolically expensive human brain is addressed. Also mitochondria capability decline with age is addressed.

ASSESSING FINANCIAL RISK TOLERANCE OF PORTFOLIO INVESTORS USING DATA ENVELOPMENT ANALYSIS

2005 ◽  
Vol 04 (03) ◽  
pp. 491-519 ◽  
Author(s):  
PARISA HOSSEINI ARDEHALI ◽  
JOSEPH C. PARADI ◽  
METTE ASMILD
Keyword(s):  
Data Envelopment Analysis ◽  
Financial Risk ◽  
Large Data ◽  
Investment Strategy ◽  
Risk Tolerance ◽  
Data Envelopment ◽  
Data Set ◽  
Personal Investment ◽  
Using Data ◽  
Financial Risk Tolerance

For some investors their own personal investment counsellors address their investment strategy; for others automated means are used. To protect investors, the Canadian Government has enacted the "Know Your Client" Act requiring that all investment dealers and vendors of securities must know their clients and advise them on the appropriate investment strategy. This paper uses Data Envelopment Analysis (DEA) in a novel manner by applying it to a large data set of answers to a number of psychological questions. A Slacks Based Model was used to estimate investor risk tolerance. The model analyses the risk profile of the investor and can be used as a guide to match the risk rating of the investment vehicles for the client. Statistical comparisons were also carried out to show how risk tolerance relates to various demographic variables. Finally, the DEA results were validated through comparisons with the commercial system already in use.

scholarly journals Life Event Detection using Conversations from Social Media

2015 ◽  
Author(s):  
Luis Moyano ◽  
Paulo Cavalin ◽  
Pedro Paiva Miranda
Keyword(s):  
Social Media ◽  
Life Events ◽  
Event Detection ◽  
Large Data ◽  
Classification Performance ◽  
Detection Task ◽  
Classification Algorithms ◽  
Data Set ◽  
Life Event ◽  
Machine Learning Classification

In this work, we explore the possibility to detecting life events from Social Media by means of machine learning classification algorithms. One important difficulty of this kind of detection task is that, typically, Social Media posts are quite short, and there is not much context provided. This lack of context usually implies strong ambiguity leading to poor classification performance. Here, we propose the use of conversations as a means to augment context and improve classification performance. We evaluate single-post vs. conversation classification performance and compare different models for the conversations classifier. Finally, we describe the performance of the different classifiers in a large data set with 20,000 posts.

Sign in / Sign up

Export Citation Format

Share Document