Analysis Of Digital Data Research Articles

Intelligent crop yield prediction system using neural networks and databases

Machine learning plays an important role in decision support and yield forecasting. This is an effective tool for determining strategies during the growing season of plants. The article proposes a method for predicting yield using a complex system consisting of a convolutional neural network (CNN), a feedforward neural network (FNN), and a SQLiteStudio database. The system includes several stages of data processing, starting with the collection and analysis of images and digital data obtained from various sources, and ending with yield forecasting based on this data. A convolutional neural network (CNN) is used to analyze images and video streams to recognize and count fruits on trees, providing accurate data about the status of the crop. Feedforward neural network (FNN) is used to analyze digital data, such as weather station data and long-term crop yield data, to subsequently predict crop yields. The received data is stored in a relational database, which ensures their structured storage and access for subsequent processing. Used SQL language to perform various database operations. To automate the process of counting fruits on trees, the YOLOv8 convolutional neural network model is used, which allows recognizing objects in real time. A Python script has been developed to process images using YOLOv8 and save the results to a database. An integrated system combines various methods and technologies to predict yields and automate data collection and analysis processes. The developed model showed a mean square error (MSE) of 7.33 and a mean absolute percentage error (MAPE) of 6.27%.

Expanding the role of justice in secondary research using digital psychological data.

Secondary analysis of digital psychological data (DPD) is an increasingly popular method for behavioral health research. Under current practices, secondary research does not require human subjects research review so long as data are de-identified. We argue that this standard approach to the ethics of secondary research (i.e., de-identification) does not address a range of ethical risks and that greater emphasis should be placed on the ethical principle of justice. We outline the inadequacy of an individually focused research ethic for DPD and describe unaddressed "social risks" generated by secondary research of DPD. These risks exist in the "circumstances of justice": that is, a circumstance where individuals must cooperate to create a public good (e.g., research knowledge), and where it is impractical to individually exempt individuals. This requires researchers to emphasize the just allocation of benefits and burdens against a background of social cooperation. We explore six considerations for researchers who wish to conduct research with DPD without explicit consent: (a) create socially valuable knowledge, (b) fairly share the benefits and burdens of research, (c) be transparent about data use, (d) create mechanisms for withdrawal of data, (e) ensure that stakeholders can provide input into the design and implementation of the research, and (f) responsibly report results. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Research on the Construction of a New Business Talent Training System in Private Colleges in the Context of the Digital Economy

In the context of the digital economy, this paper explores how private higher education institutions can construct a contemporary business education talent development system. The analysis delves into the present challenges confronting business education in private colleges, proposing a set of strategies including reforms in the curriculum, innovation in teaching methodologies, and the integration of industry and education. A significant emphasis is placed on the necessity of digital technology and data analysis skills, as well as cross-cultural communication and collaborative abilities for business professionals. The objective of this research is to enhance the adaptability and practical effectiveness of business education, in order to fulfill the societal demand for highly qualified business professionals.

ПРОЕКТ ЭМПИРИЧЕСКОЙ ШКАЛЫ ЦИФРОВОЙ ТРАНСФОРМАЦИИ ПРОИЗВОДСТВЕННЫХ ПРЕДПРИЯТИЙ КИТАЯ

Digital transformation has become an important way to achieve high-quality growth of manufacturing enterprises. The article is devoted to a questionnaire on this topic, the purpose of which is to obtain useful information. Respondents should not only collect the necessary data, but also ensure their accuracy. The work is based on the theories of innovation, technical and economic paradigm. References are given to the literature of relevant scientists in terms of IT capabilities, organizational culture, leadership issues, digital customer orientation, data analysis and decision-making, and digital transformation strategies. The article is prepared in accordance with the cognitive habits of Chinese manufacturing enterprises.

REVISITING KEY CONCEPTS IN DIGITAL MEDIA RESEARCH: INFLUENCE, POPULISM, PARTISANSHIP, POLARISATION

Recent scholarship on the intersections between digital media and political debate has taken on a decidedly pessimistic, even dystopian tone, and not without reason: from the effective use of social media platforms by populists and demagogues like Donald Trump to the expression of deepening ideological divides in online public debate, and from the emergence of partisan online communities and platforms to the intensification and exploitation of such partisanship by conspiracy theorists and state actors, there are substantial concerns about the way that extremist actors are utilising digital and social media logics to further their ideological agendas. The situation is further complicated by platform providers’ and regulators’ limited and unsystematic responses to these issues. But while there is considerable research into the various issues and events that illustrate these developments, many of the central concepts that are used to describe these cases receive substantially less critical attention. Terms such as ‘influence’, ‘populism’, ‘partisanship’, and ‘polarisation’ are often deployed as if did not themselves require further qualification and definition – even in spite of the considerable volume of literature in political science and other ancillary disciplines that addresses the various facets that such concepts may have. Informed by and building on substantial empirical research, this panel therefore facilitates a conversation between methodological innovation at the coalface of digital trace data analysis and careful reflection on the definitions of key concepts, in order to explore the conceptual frameworks and methodological approaches that might illuminate the distinct features of our four key concepts in sharper focus. Our first paper engages with the concept of influence, which it conceptualises as the power to affect others. Focussing especially on the spread of verified false content (VFC) through social media, it proposes a novel population-scale approach that both employs a bottom-up perspective for identifying the influential actors spreading such content, and highlights the exposure of ordinary citizens to these messages. It demonstrates this approach by drawing on the large-scale Facebook URL-sharing dataset available from Social Science One, developing an EU-wide perspective on VFC exposure at national levels. Our second paper continues this approach by critiquing the concept of populism, highlighting the term as a weak analytical concept. It argues that, rather than focussing on their populist stance, populist politicians can be judged by the extent of their delegitimising rhetoric. Further, the paper asserts that such rhetoric is enabled by the decentralised communication environment of social media. The utility of the concept of delegitimisation is that enables the identification of political messages that are truly dangerous because they are meant to destabilise fundamental democratic principles, such as the integrity of the vote and the legitimacy of alternative policy perspectives. By situating this in the context of social media messaging, we can see how such messages are amplified by distributed network channels. Our third paper shifts focus to the possible results of influence campaigns and populist demagoguery, and addresses the concept of partisanship. Taking as case study the 2022 Italian election, it introduces a novel combination of computationally informed analytical methods and applies them to social media data to gauge the level of partisan attention devoted to the different news sources and political topics in the election campaign, and distinguish between partisan and cross-partisan sources and themes. This provides new insights into the structures, intersections, and faultlines of partisanship, and enables the mapping of a broader multi-dimensional ideological space. Our final paper continues this discussion by exploring the complexities of polarisation. It highlights the conceptual fluidity of this term, which is expressed in the multitude of adjectives and qualifiers that can be found in the relevant literature – from ideological through affective to interactive polarisation and beyond, and from benign and even beneficial to pernicious and destructive polarisation. Mapping these distinct forms of polarisation onto a diverse range of mixed-methods digital media research approaches, and outlining a number of criteria for assessing whether the dynamics of polarisation have turned destructive, it outlines new pathways for polarisation research in Internet studies. In combination, then, these four papers offer a timely nudge for digital and social media research to revisit and reconsider some of the central concepts in online political communication studies, and to retrace and reaffirm the connections between the definitions of these concepts and the methodological frameworks that we use to study them.

Integrating Human-Computer Interactions in Nigerian Energy System: A Skills Requirement Analysis

The energy sector constitutes an important contributor to the growth and development of the Nigerian economy. Despite Nigeria's abundant energy resources, the sector faces multiple challenges, such as infrastructural deficits, policy inconsistencies, regulatory uncertainties, and overreliance on non-renewable energy sources. Industry 4.0 technologies and Human-Computer Interaction (HCI) present opportunities that address the challenges of the energy sector in Nigeria. This research explores the impact of HCI in the adoption of technologies of 4IR (Artificial Intelligence, the Internet of Things, Big Data, and Cloud Computing), in Nigeria's energy sector. The research assesses the current level of implementation of Industry 4.0, requirements for the implementation of Industry 4.0 technology, demand, and skills for HCI in the implementation of 4IR technology in Nigeria's energy generation sub-sector. This study adopted a comprehensive and critical systematic review of existing literature on the subject matter. The findings reveal the level of 4IR implementation in its infancy, with some energy companies and start-ups beginning to integrate digital technologies to enhance their operations and services. The study further revealed the potential of HCI in facilitating the integration and social acceptance of 4IR technologies and identified significant skills demand for HCI, such as digital literacy, data analysis, critical thinking, problem-solving, and system thinking to facilitate the adoption of 4IR. The research concludes that the development of HCI skills in the adoption of 4IR presents a great opportunity to transform the energy sector in Nigeria. The research recommends policy formulation, to embrace Industry 4.0 and multifaceted process development of HCI skills for the application of 4IR in the energy sector.

Bibliometric Analysis: Application of Blended Learning in the Development of Digital Skills in the Era of Digital Education

In the current era characterized by rapid and widespread technological progress, digital skills have become an important factor in shaping individual success and societal progress. Digital skills cover a wide range of proficiencies, including digital literacy, programming, data analysis, online collaboration, and information security. In the world of education, a lot of research has been carried out on digital skills, one of the most research topics is the application of blended learning to improve digital skills. Therefore, researchers conducted a bibliometric analysis of the application of blended learning in developing digital skills in the era of digital education which aims to conduct a comprehensive exploration of existing literature. This research involved a comprehensive approach combining a systematic literature review and bibliometric analysis to explore the development of digital skills through online learning and assess its impact. Additionally, the use of VOSviewer software to visualize bibliometric networks is also discussed. The research results show that six different thematic clusters were found in the literature on digital skills development in the digital education era. Each cluster summarizes a set of recurring keywords that describe existing research trends, providing valuable insight into the landscape of the field. It can be concluded that this research contributes to the growing understanding of digital skills development through online learning and highlights its transformative potential in the world of education.

Геолого-геоморфологическое районирование бассейна р. Сейды (восток Большеземельской тундры) на основе цифровой модели рельефа ArcticDEM

The Bolshezemelskaya tundra is one of the least studied and poorly mapped territories of the European North-East of Russia. The availability of the ArcticDEM digital elevation model with a high spatial resolution allowed conducting a comprehensive joint analysis of digital, geomorphological and geological data.
 The results of using the ArcticDEM global digital relief model for geological and geomorphological studies of the Seyda River basin (eastern Bolshezemelskaya tundra) in its middle and lower reaches are presented.
 An irregular triangulation network TIN covering the Seyda River valley was constructed, and the main geomorphometric parameters of the relief were calculated: hypsometric characteristics, surface inclination angles and slope exposures. Based on the obtained morphometric indicators of the relief and the textural and structural characteristics of Quaternary sediments, the following types of relief were identified: accumulative glacial, erosion-accumulative water-glacial and erosion-accumulative alluvial types of relief. A geological and geomorphological diagram of the Seyda River valley was been constructed and the main morphogenetic features of the relief during its formation were identified.

Solar Observations by Angelo Secchi. I. Digitization of Original Documents and Analysis of Group Numbers over the Period of 1853–1878

Angelo Secchi, an Italian Jesuit and prominent scientist of the 19th century, and one of the founders of modern astrophysics, observed the Sun regularly at the Collegio Romano in Rome, Italy, for more than 25 yr. Results from his observations are reported in articles published in the scientific journals of the time, as well as in drawings and personal notebooks that are stored in the historical archive of the Istituto Nazionale di Astrofisica Osservatorio Astronomico di Roma. The latter material, which reports solar observations performed from 1853–1878, includes original documents from Secchi and from a few of his close collaborators. The above unique material has recently been digitized for preservation purposes and for allowing the scientific exploitation of data not easily accessible so far. A total of more than 5400 digital images have been produced. Here we present the archival material and the new digital data derived from it. We also present results obtained from our primary analysis of the new digital data. In particular, we produced new measurements of the group number from 1853–1878, which will be available for future recalibration of the group number series.

Digital supply chain surveillance using artificial intelligence: definitions, opportunities and risks

Digital Supply Chain Surveillance (DSCS) is the proactive monitoring and analysis of digital data that allows firms to extract information related to a supply network, without the explicit consent of firms involved in the supply chain. AI has made DSCS to become easier and larger-scale, posing significant opportunities for automated detection of actors and dependencies involved in a supply chain, which in turn, can help firms to detect risky, unethical and environmentally unsustainable practices. Here, we define DSCS, review priority areas using a survey conducted in the UK. Visibility, sustainability, resilience are significant areas that DSCS can support, through a number of machine-learning approaches and predictive algorithms. Despite anecdotal narrative on the importance of explainability of algorithmic results, practitioners often prefer accuracy over explainability; however, there are significant differences between industrial sectors and application areas. Using a case study, we highlight a number of concerns on the unchecked use of AI in DSCS, such as bias or misinterpretation resulting in erroneous conclusions, which may lead to suboptimal decisions or relationship damage. Building on this, we develop and discuss a number of illustrative cases to highlight risks that practitioners should be aware of, proposing key areas of further research.

Addressing Challenges and Outcomes in the Biogas Sector: An Analysis of Efficiency, Economic Savings, and Environmental Impacts Using an Advanced SWOT Model

This study, through the use of company data, offers an in-depth analysis of the current situation and future prospects of biogas plants and how they can promote economic advantages and environmental benefits. The geographical context of the Piana del Sele (Salerno, Italy) was chosen on the basis of objective criteria, including its relevance in the agro-industrial sector and the availability of accurate and reliable company data that was collected through IT systems, including software business performance monitoring and digital data analysis. This choice was fundamental to guaranteeing the validity and representativeness of our analyses and results. From a methodological point of view, mathematical formulas and algorithms were used, which allowed the calculation of the biogas producibility indices by type of biomass as well as the quantification of the effluents produced to then estimate the quantification of the biogas and the interconnected economic savings. Furthermore, this study uses the SWOT (strengths, weaknesses, opportunities, and threats) approach in an innovative way by integrating renewable energy communities into it. The aim is to demonstrate the potential of biogas plants and how energy communities can transform weaknesses and threats into opportunities. The results show that the integration of biogas plants into the farm environment offers considerable potential, and although it is a challenge for small and medium-sized farms, it could bring energy self-sufficiency and economic surplus. Furthermore, the integration of renewable energy communities would be able to promote the diversification of energy supply and transform weaknesses and threats into opportunities.

Digital Polymerase Chain Reaction (dPCR) Versus Flow Cytometry (FC), a Validation Study for CAR-T Cell Product Optimal Detection

CONCLUSIONS Adoptive immunotherapy with Chimeric Antigen Receptor - T cells (CAR-T), has revolutionized hematological treatment mainly in relapsed/refractory (r/r) B-cell malignancies. CAR-T cells constitute challenging living drugs with heterogeneous in vivo cellular kinetics and adverse side effects that emphasizes the importance of its accurate detection and monitoring. Diagnostic assays are required for precise CAR-T quantification. Digital PCR (dPCR) is characterized by a high specificity, sensitivity and reproducibility, therefore we developed a study to implement this technique for CAR-T detection and compare its efficacy against Flow Cytometry (FC). Duplex dPCR assays were performed to concomitantly amplify CAR and RPP30 (reference gene) sequences using ddPCR Expert Design Assay: CD-19 CAR-T Assay (Bio-Rad, California, USA) with QIAcuity Digital PCR System and data analysis with QIAcuitySoftware Suite (QIAGEN, Germany). To assess sensitivity, a Axicabtagene Ciloleucel (Axi-Cel ®) original product obtained from leftovers's infusion bag patient was employed to perform dPCRs on serial dilutions using genomic DNA(gDNA) from a wild type (WT) patient. Specificity was ensured using WT and no template controls (NTC). Two independent dPCR assays with replicates for each sample were conducted to assess reproducibility. For FC comparative study, CAR-T cells percentage (%CAR-T) was determined by both techniques at variable post-infusion intervals (n=210) in different sample types, peripheral blood (n=205) and cerebrospinal fluid (n=5). Anti-FMC63 scFv Antibody, Mouse IgG1 (Acro biosystems) was employed, using FACSCanto II®, Becton-Dickinson Biosciences with FACSDiva software ® (V8.0; BD) and InfinicytTM software (Cytognos SL, Salamanca, Spain), for data analysis. Correlation coefficients were determined using two-tailed Pearson statistics with a confidence interval of 95%. Statistical analyses were made with SPSS Software (IBM, Germany). The dPCR data collected of 2 independent dPCR assays revealed a good split between the negative and positive partitions for the targets evaluated, showing a progressive decrease of the %CAR-T detected (63,88% - 4,12% - 0,77% - 0,08% - 0,01% - 0,00%). This reduction is correlated with the dilution factor applied to the series with an initial concentration of 50ng/µL both for CAR-T original product and WT gDNA. WT and NTC samples were negative with a SD=0; %CV=0, intra and inter-assays, evidencing thus the specificity of the technique. Positivity of the last (1 pg/µL) samples revealed a maximum sensitivity of 0.009 %CAR-T, threshold below which false positive results would be considered. WT gDNA did not influence the assay's sensitivity. 3 replicates of each sample and 2 independent dPCR assay were performed to study potential variations, exhibiting an excellent intra and inter-assay reproducibility with a minimal SD across dilutions ( Table.1.) Comparative study with FC revealed a light correlation between techniques with a Pearsons's correlation coefficient (R=0,553) ( p<0,001). Differences among both were enhanced for Minimal Residual Disease (MRD) evaluation from 60 days post-infusion monitoring (R=0,58) ( p=0,066) in which CAR-T cells can be detected applying dPCR up to 2 years and 9 months post-infusion, whereas being undetectable by FC. Complex CAR-T in vivo kinetics enhances the need for optimal diagnostic and monitoring techniques. dPCR is an ideal tool for precise CAR-T therapy evaluation with a higher grade of specificity, sensitivity and reproducibility than FC, mainly for MRD assessment. dPCR implementation and the establishment of standardized protocols across centers is required to improve CAR-T biology knowledge with a direct benefit on patient care.

Digitalization of maintenance activities in small and medium-sized enterprises: A conceptual framework

Asset management and digitalization are two timely research topics, especially for small and medium-sized enterprises (SMEs). SMEs continue to struggle with implementing digital technologies while retaining effective asset management processes within maintenance and after-sales service. Therefore, this paper develops a conceptual framework that integrates technological and organizational factors for digitalizing maintenance processes in SMEs. Furthermore, this paper steps away from the prevalent high-tech narrative, to explore how SMEs practically can implement digital technologies amidst common constraints. A focal point of this study is leveraging existing technologies and data for low-cost optimizations as a practical steppingstone for SMEs, bridging the gap between high-tech digital discussions and SMEs' real-world scenarios. The framework addresses three theoretical challenges in the existing literature, drawing on multiple case studies, and employing pragmatic research methods. It offers a conceptual tool for assessing the digital maturity of maintenance processes in SMEs and identifying areas for improvement. Based on the framework, low-performing domains across the case studies are pinpointed for future research. These domains encompass technical competencies within information systems, strategic efforts, and human capital within prototyping, and organizational culture within digital data collection and analysis.

Correlational Study of Channels of Digital Advertising and Consumers’ Behaviour: A Study of Delta State

The study seeks to find out the correlation between channels of digital advertising and consumers’ behaviour by looking into the processes of consumer behaviour through the usage of smart gadgets. Digital advertising harnesses the capabilities of digital technology, data analysis, and online channels to create targeted, measurable, and impactful advertising campaigns in the ever-evolving digital landscape. Hinged on the technological determinism theory, the study employed the survey design using 400 copies of structured questionnaire to get data from respondents. To test the hypothesis, 392 copies of properly filled and retrieved questionnaire were analysed using Stata 15.0 software application. The study affirms the spread of social channels, as well as high-quality, low-cost technology, is fuelling the growth of digital advertising. The study establishes that digital advertising may influence brand impression and awareness, as well as generate favourable attitudes toward the offered items. Research, marketers, and advertisers may get useful insights on how to use content aspects to persuade customers to have a good attitude towards advertised products and brands.

A digital ecosystem for the multidisciplinary study of Notre-Dame de Paris

The 2019 fire of Notre-Dame de Paris was not only a significant event in its history, but also provided a unique platform for multidisciplinary studies and digital data analysis. At the initiative of the CNRS and the Ministry of Culture, a large-scale collaboration is currently underway to manage and analyse the extensive data generated in connection with the restoration of the cathedral. The role of digital data is crucial for understanding complex multidisciplinary studies, especially in the field of cultural heritage. A digital data working group, composed of thirty scientists from 12 laboratories, is focused on documenting and organising this collective experience to serve both the immediate needs of restoration and the long-term goals of cultural heritage research. Key challenges include data traceability, knowledge modelling, multidimensional analysis and the need to address gaps in semantic understanding, memory, data correlation and technology. To address these challenges, a novel method is proposed that combines the digital representation of material heritage with the evolving knowledge about it. By collaborating with the wider scholarly community involved in Notre Dame's scientific action, the aim is to introduce new methods in heritage research and bridge the gap between the humanities and digitally-driven scholarship. This initiative also intersects with two primary scientific vectors: the technological approach to data collection and the generation and analysis of semantically enriched datasets.

Data Analytics and Personalized Marketing Strategies in E-commerce Platforms

The purpose of this study is to identify the most adapted digital data analysis tools for developing individual marketing strategies in the e-commerce segment. In the study the following ranking methods were used: the cross-expert rating (based on individual opinions of 15 specialised organisations) and arbitration rating of the most relevant resource - G2.com. Subsequently, a comparative analysis of the leading E-Commerce Analytics applications was performed in order to obtain the ranking results. Using a methodology that took into account the expert ratings, cross- and arbitrage ratings, as well as the user feedback, it was found that the Glassbox was the best option for large enterprises, particularly, for large e-businesses. Google Analytics, on the other hand, is more popular among smaller companies and is considered a more versatile tool for data analysis. The importance of choosing the right tool for data analytics in e-commerce was also highlighted in the study, as the wrong choice can lead to financial losses and loss of investment. Future researches in this area include the creation of universal algorithms for selecting data analytics software solutions, expanding the range of data analytics applications, and more detail in understanding the specific needs of e-commerce platforms.

Data donation of individual shopping data to help predict the occurrence of disease: A pilot study linking individual loyalty card and health survey data to investigate COVID-19

Introduction & BackgroundPrevious studies have found shopping data could increase the predictive accuracy of disease surveillance systems and illuminate behavioural responses in the self-management of symptoms of disease. Yet, accessing individual sales datasets for linkage to health datasets is challenging, and the recruitment of appropriate sample sizes for medical research has been limited.
 Objectives & ApproachObjectivesCollect and link individual health data to individual shopping data to investigate COVID-19. Assess the feasibility of scaling-up this method, and use the collected data to investigate using loyalty card data in machine learning (ML) models for disease.
 MethodsBased on recommendations on the public’s preferences for data donation a new protocol was designed for collecting, linking and analysing shopping and health data. Participants were requested to use the Tesco Clubcard website data portability function to share their loyalty card data and complete an online health survey. An exploratory data analysis was conducted on the linked dataset. Participants were recruited online (18/01/2022 to 04/02/2022) with a recruitment target of 200.
 Relevance to Digital FootprintsThe collection and analysis of individual transactional sales data for health research.
 Results197 participants shared their Tesco Clubcard and health survey data. Tesco Clubcard data contained 893,414 transactions of 65,310 uniquely named items purchased from 2015 to 2022. Average transactions per participant were 4,653 (SD 5256) and average timeframe recorded was five years 6 months and 30 days (SD 836 days). A total of 6,993 medication sales were recorded accounting for 1% of sales, 81% (159/197) of participants bought medications and the average was 44 (STD 68) medications per individual. Most participants (196/197) shared their health status in the survey, and 94% (81/86) of those on medication shared the medication names. Participants reported donating their data to do good (79%, 155/197), help the NHS (77%, 152/197), be socially responsible (74%, 144/197) and because data was secure and anonymised (78%, 153/197).
 Conclusions & ImplicationsUsing this new protocol which enables convenient data sharing with transparent data safeguards, the public were willing to share both their shopping and health data for research into COVID-19. To apply robust ML analysis, particularly to explore self-medication at an individual level, recruitment must be significantly scaled to collect data from enough individuals with high sales and regular shopping frequency, or new ML techniques developed to address sparseness in loyalty card data of key purchasing events related to health. The study suggests public readiness to share shopping data for health research, but investment is needed for large-scale data collection and AI application.

Generating a Single Session Outcome Measure from Digital Mental Health Platform Footprints Using Natural Language Processing

Generating a Single Session Outcome Measure from Digital Mental Health Platform Footprints Using Natural Language Processing

Decoy Effects in a Massive Real-World Shopping Dataset

Introduction & BackgroundA key premise of rational choice prescribes that decision-makers ought to ignore irrelevant, inferior alternative options. Consider for example the choice between two wines, where the value of an option is computed across two dimensions: quality and price. When deliberating about which wine to choose, one’s propensity to choose between two otherwise equally preferred wines should be not influenced by the introduction of a third clearly inferior option (being both of lower quality and more expensive than one of the original alternatives). Yet, a large body of work suggests that both people and animals routinely violate this premise in their decisions—in laboratory experiments, the introduction of irrelevant “decoys” into a choice set biases decision-making. However, these decoy effects are less understood in large-scale contexts of real-world decision-making, where choice sets can be large, and preference informed by consumers’ histories of experience.
 Objectives & ApproachWe explored whether the presence of irrelevant, “decoy” alternative options influenced wine purchases in a large real-world dataset of UK wine purchases. From shopping transaction records, we extracted all red and white wine purchases over a one month period. Our analyses examined 3.6M wine purchases made by 755,158 unique customers.
 Relevance to Digital FootprintsWe deployed shopping history data which is a popular example for digital footprints allowing us to track people’s choices and decisions over long periods of time.
 ResultsWe find that among pairs of wines that appear across many different contexts (i.e., stores with different product assortments) and trade off on quality and price, the presence of decoy options— similar options that were dominated by the focal option—made consumers more likely to purchase the focal option (a hallmark of the “attraction effect”). Furthermore, we find that sensitivity to this effect depended on consumers’ history of experience with the product, such that frequent shoppers were less likely to be sensitive to decoy effects in their purchase behaviour.
 Conclusions & ImplicationsWe examined whether real-world consumer decisions, evidenced in a large dataset of wine purchases in the United Kingdom, were subject to a canonical bias in multiattribute choice: the attraction effect. We found that wine purchases were systematically biased in favour of wines that dominated choice sets—a bias which was not observed when choice sets were not dominated. Together, these results extend laboratory-based accounts of decoy effects to real-world choices, and demonstrate how digital footprints data analysis can be linked to health, especially in terms of decision making which is associated with negative health outcomes.

Beyond Comparative Analysis: Making Arguments with Similarity Metrics and Structured Manuscript Data, with a Case Study in Marginal Iconography

Abstract: Quantitative measurements of similarity can help researchers understand the increasing amount of manuscript metadata or digital images now available for study. Researchers in archaeology, ecology, and information retrieval have developed diverse methods for quantifying the similarity of categorical, numerical, and presence/absence data. The variety of methods in use reflects the complex associations of the term "similarity" and suggests that quantitative approaches can preserve some of the nuance associated with traditional humanistic approaches. We argue that similarity metrics, contextualized against random simulations, provide flexible tools for identifying and analyzing trends in large sets of multifaceted historical data and can be applied to many kinds of manuscript research projects. Simulations (permutation tests) that highlight how observed patterns diverge from random or theoretical scenarios have allowed us to interpret similarity measurements against a baseline that is analogous to researchers' intuitions born of experience. In this paper, we model using similarity metrics to conduct multifaceted analyses of an iconographic dataset derived from Lilian M. C. Randall's Images in the Margins of Gothic Manuscripts (1966), indexing images in French, English, and Flemish manuscripts produced between about 1250 and 1350. We share examples of approaches such as statistical analysis, Analysis of Similarity, and clustering to model the type of quantitative approaches we believe will become increasingly important for the analysis of digital manuscript data.