Instagram Data Research Articles

CRITICAL SIMULATION: INVESTIGATING THE WORK OF MACHINE VISION IN VISUAL SOCIAL MEDIA CULTURE

Social media are in the midst of an emphatic visual turn (Highfield & Leaver 2016), characterised by the convergence of everyday visual expression with professional creative practice and advertising. The advertising-driven business models of social media platforms increasingly depend on automation. Platforms’ use of machine vision is a key frontier in the algorithmic classification of culture. Machine vision algorithms automatically classify and misclassify faces, expressions, objects, and brand logos in the images users create and share. Images shared by platform users form vast databases used to train these same algorithms. Despite widespread use by social platforms, machine vision is poorly understood and accounted for in the study of everyday visual cultures. In this paper we detail a critical response to the use of automation in visual social media, called critical simulation. We outline a critical simulation framework, the ‘Image Machine’, focussed firstly on Instagram. The Image Machine comprises an Instagram data harvester, and open-access machine vision toolbox that allows digital humanities researchers to interrogate the inner workings of these algorithms and analyse their visual (mis)classifications. In this paper we showcase results from the Image Machine applied to images emanating from a major Australian music festival, Splendour in the Grass. This case examines not only how machine vision classifies and operates on culture, but also how these techniques are being operationalised within the advertising model and promotional culture of platforms like Instagram. We argue that the commercial application of machine vision is interdependent with the participatory culture of platforms like Instagram.

TOURISTS GEOVISUALIZATION ANALYSIS UTILIZING INSTAGRAM DATA IN CENTRAL JAVA PROVINCE AND SPECIAL REGION OF YOGYAKARTA

Abstract. The growth of Indonesia‟s national economy in the sector of tourism has been improving constantly. Based on BPS data year 2015, tourism has contributed to PDB with the amount of 4,25%. Tourists is an important aspect because they play a role in the economic change in tourism. Along with social media development, tourists‟ distribution can be monitored using big data in social media. Instagram is one of the social media which is often used by tourists to share photos or videos while traveling. Issues that appeared when using big data Instagram to produce spatial data are size, variation, and a big time span. This research is aimed to extract big data Instagram to produce basic tourists’ spatial data and analyze tourist attractions using geovisualization hexagonal tessellation in West Java Province and Special Region of Yogyakarta. Generally, the methods used are divided into three which are data mining, graphic visual analysis and geovisualization classification hexagonal tessellation. The Instagram data extraction process uses a web-based software called Netlytic, while pre-processing data to produce tourists’ spatial data uses QGIS software. Hexagonal tessellation is tested by graphic visual to ensure the most effective measurement in the scale of 1 : 1.250.000. The most effective hexagonal tessellation measurement is used to classify tourist attractions. Based on the results, it shows that the most effective measurement of hexagonal tessellation is 2 Km. The most popular tourist attraction is Malioboro Yogyakarta based on hexagonal tessellation geovisualization analysis.

Can acute suicidality be predicted by Instagram data? Results from qualitative and quantitative language analyses.

BackgroundSocial media has become increasingly important for communication among young people. It is also often used to communicate suicidal ideation.AimsTo investigate the link between acute suicidality and language use as well as activity on Instagram.MethodA total of 52 participants, aged on average around 16 years, who had posted pictures of non-suicidal self-injury on Instagram, and reported a lifetime history of suicidal ideation, were interviewed using Instagram messenger. Of those participants, 45.5% reported suicidal ideation on the day of the interview (acute suicidal ideation). Qualitative text analysis (software ATLAS.ti 7) was used to investigate experiences with expressions of active suicidal thoughts on Instagram. Quantitative text analysis of language use in the interviews and directly on Instagram (in picture captions) was performed using the Linguistic Inquiry and Word Count software. Language markers in the interviews and in picture captions, as well as activity on Instagram were added to regression analyses, in order to investigate predictors for current suicidal ideation.ResultsMost participants (80%) had come across expressions of active suicidal thoughts on Instagram and 25% had expressed active suicidal thoughts themselves. Participants with acute suicidal ideation used significantly more negative emotion words (Cohen’s d = 0.66, 95% CI: 0.088–1.232) and words expressing overall affect (Cohen’s d = 0.57, 95% CI: 0.001–1.138) in interviews. However, activity and language use on Instagram did not predict acute suicidality.ConclusionsWhile participants differed with regard to their use of language in interviews, differences in activity and language use on Instagram were not associated with acute suicidality. Other mechanisms of machine learning, like identifying picture content, might be more valuable.

Hashtag Recommendation for Photo Sharing Services

Hashtags can greatly facilitate content navigation and improve user engagement in social media. Meaningful as it might be, recommending hashtags for photo sharing services such as Instagram and Pinterest remains a daunting task due to the following two reasons. On the endogenous side, posts in photo sharing services often contain both images and text, which are likely to be correlated with each other. Therefore, it is crucial to coherently model both image and text as well as the interaction between them. On the exogenous side, hashtags are generated by users and different users might come up with different tags for similar posts, due to their different preference and/or community effect. Therefore, it is highly desirable to characterize the users’ tagging habits. In this paper, we propose an integral and effective hashtag recommendation approach for photo sharing services. In particular, the proposed approach considers both the endogenous and exogenous effects by a content modeling module and a habit modeling module, respectively. For the content modeling module, we adopt the parallel co-attention mechanism to coherently model both image and text as well as the interaction between them; for the habit modeling module, we introduce an external memory unit to characterize the historical tagging habit of each user. The overall hashtag recommendations are generated on the basis of both the post features from the content modeling module and the habit influences from the habit modeling module. We evaluate the proposed approach on real Instagram data. The experimental results demonstrate that the proposed approach significantly outperforms the state-of-theart methods in terms of recommendation accuracy, and that both content modeling and habit modeling contribute significantly to the overall recommendation accuracy.

Drinks & Crowds

The design of computational methods to recognize alcohol intake is a relevant problem in ubiquitous computing. While mobile crowdsensing and social media analytics are two current approaches to characterize alcohol consumption in everyday life, the question of how they can be integrated, to examine their relative value as informative of the drinking phenomenon and to exploit their complementarity towards the classification of drinking-related attributes, remains as an open issue. In this paper, we present a comparative study based on five years of Instagram data about alcohol consumption and a 200+ person crowdsensing campaign collected in the same country (Switzerland). Our contributions are two-fold. First, we conduct data analyses that uncover temporal, spatial, and social contextual patterns of alcohol consumption on weekend nights as represented by both crowdsensing and social media. This comparative analysis provides a contextual snapshot of the alcohol drinking practices of urban youth dwellers. Second, we use a machine learning framework to classify individual drinking events according to alcohol and non-alcohol categories, using images features and contextual cues from individual and joint data sources. Our best performing models give an accuracy of 82.3% on alcohol category classification (against a baseline of 48.5%) and 90% on alcohol/non-alcohol classification (against a baseline of 65.9%) using a fusion of image features and contextual cues in this task. Our work uncovers important patterns in drinking behaviour across these two datasets and the results of study are promising towards developing systems that use machine learning for self-monitoring of alcohol consumption.

SEMANTIC VALIDATION OF SOCIAL MEDIA GEOGRAPHIC INFORMATION: A CASE STUDY ON INSTAGRAM DATA FOR EXPO MILANO 2015

Abstract. Social media data, such as Instagram posts, can be associated with spatial positions. This information can be exploited to perform spatial analyses, such as identifying distribution patterns of points representing the positions of social media users during an emergency or while attending a specific event or exhibition. However, the geolocation provided by Social Media Geographic Information (SMGI) needs to be validated, in order for the spatial data to be used in a meaningful way in subsequent spatial analyses or mapping procedures. In this paper, a case study is presented based on Instagram data collected during the first two months of the Expo Milano 2015 exhibition, where the spatial data have been validated by exploiting the semantic component of the posts.

Measuring the size of a crowd using Instagram

Measuring the size of a crowd in a specific location can be of crucial importance for crowd management, in particular in emergency situations. Here, using two football stadiums as case studies, we present evidence that data generated through interactions with the social media platform Instagram can be used to generate estimates of the size of a crowd. We present a detailed analysis of the impact of varying the time period and spatial area considered for the collection of Instagram data. Crucially, we demonstrate how to address issues that arise from changes in the usage of a social media platform such as Instagram. Our findings show how social media datasets carrying location-based information may help provide near to real-time measurements of the size of a crowd.

Urban events prediction via convolutional neural networks and Instagram data

In today’s world, it is crucial to be proactive and be prepared for events which are not happening yet. Thus, there is no surprise that in the field of social media analysis the research agenda has moved from the development of event detection methods to a brand new area - event prediction models. This research field is extremely important for all sorts of applications, from natural disasters preparation and criminal activity prevention to urban management and development of smart cities. However, even the leading models have an important disadvantage: they are based on prior knowledge about events being expected. So forecasting systems based on such models are heavily limited by a list of events that can be predicted and all events of other types will be out of systems’ scope. In this work, we try to address this issue and propose a deep learning model, which is able to predict an area of the future event in the urban environment. This model is able to predict the future state of the city - a level of users activity in the location-based social network Instagram - with the average deviation from the ground truth of 1%, and achieves 69% recall when solving the events prediction problem.

The use of Location Based Instagram Data for Tourism Potential Analysis in Kabupaten Gunung Kidul

Gunungkidul Regency is one of five regencies in Yogyakarta Province which is rich of natural tourism destination objects. Each tourism object has its own potential and characteristic that distinguishes one with other tourism objects. However, the tourism potency have not been exposed to public properly, and the local government has not sufficiently use the data of visitors as the basis for planning and development of tourism objects in Gunungkidul Regency. This research tries to evaluate the use of BIG DATA, especially social media data, to analyze the tourism potency based on the public opinions and visits. For this purpose, Instagram data was utilized as the main data for the analysis. The data was collected between December 18, 2017 to February 3, 2018 using Instagram API. The data then was pre-processed to clear or filter the duplication data, to filter the data based on selective location or study area namely Gunungkidul Regency, as well as to filter the data which match with the topic of the research namely “tourism”. Some analysis then were conducted, namely spatial analysis, statistical analysis, and caption analysis. The spatial and statistical analysis were aimed to find spatial pattern of tourists visits at several locations in the form of spatial density of each tourism destinations with respect to temporal aspect. Analysis of captions is done by filtering Instagram data by using some keywords that can indicate tourism potency. Data was visualized using Carto Builder. Results show that some effort is needed to utilize the Instagram data for this purpose. The data is efficient and effective to be used to visualize spatial-temporal pattern of visitors at tourism destinations, as well as to understand tourism destinations objects potency in Gunungkidul Regency. However, this analysis cannot be done in realtime due to a limitation in collecting data from Instagram API.

Analysis of activities in social media polish men's volleyball clubs of PlusLiga

The article has been written in order to present activities in social media of PlusLiga teams in Polish men's volleyball sport clubs. The aim of this report is to show the diversified social media management (Facebook and Instagram in particular) influence on the recipients statistics. The main research method for the given article is data obtained from club profiles on Instagram and Facebook. The Instagram data has underwent a detailed analysis as this social medium is one of the main tools of sports marketing, building and promoting a good image of sports teams. Thanks to the information provided, it is possible to determine at what stage is the social media sports marketing of the PlusLiga clubs. Eight teams with different positions in the league table from season 2017/18 were selected for the study. The presented results and charts are an original work and can be used to analyze the development of social media activities of men's volleyball teams.

SNS 사용자에 의해 형성된 트렌드 중심지 도출을 위한 빅 데이터 분석 방법론 연구 : 인스타그램 데이터 활용 공간분석을 중심으로

최근 새롭게 등장하는 핫스팟 지역과 트렌드 중심지는 SNS를 이용하는 골목러(골목 구석구석을 탐색하며 자신 만의 멋집 및 맛집을 찾아 SNS로 공유/홍보하는 사용자)들에 의한 바이럴 효과로 인해 골목 및 블록 등으로 세분화되어 움직이는 현상이 나타나고 있다. 따라서 유의미한 트렌드 중심지(상권 및 핫 플레이스)를 파악함에 있어서, 국가에서 정의하는 상권분석 데이터 및 지하철역, 쇼핑몰 상가 등 대형집객시설과 유동인구수 등의 거시적인 지표만으로는 한계가 있으며, SNS 사용자 데이터를 활용한 면밀한 분석이 필요하다. 본 연구는 사용자에 의해 형성되는 트렌드 중심지 파악을 위해 최근 급부상하는 SNS인 인스타그램 데이터를 활용하여 “소셜 빅 데이터 분석 방법론”을 구축하고 검증하였다. 트렌드 중심지 도출을 위한 빅 데이터 분석 기법으로 국지모란지수법을 활용하여 공간분석 모델을 개발하였고, 개발된 분석 모델을 기반으로 인스타그램 데이터에 대한 공간분석을 수행하였다. 소셜 빅 데이터에 대한 공간분석 결과, 국가 지정의 국내 기존 상권 정보에는 나타나지 않는 “SNS 사용자 데이터 기반의 새로운 트렌드 중심지”가 도출되었다. 본 연구에서 제시된 분석 방법론을 통해, SNS를 활용하여 빠르게 변화하는 최신 트렌드 지역을 보다 명확하게 파악할 수 있으며, 소상공인 및 골목상권 상인들의 창업, 마케팅 등에 활용될 수 있는 유용한 실무 정보를 제공할 수 있을 것이다. 본 연구에서 제안된 분석 방법론은 앞으로 다양한 소셜 빅 데이터 연구에 활용될 수 있을 것이다.

INSTAGRAM SELFIE DI PAMERAN ARTJOG

Instagram Selfie in ArtJog exhibition is a research conducted with purpose to identify how selfie done with artwork in an art exhibition using social media as well as to determine the effect of social media on the art exhibitions visitor. The object of this study is limited to selfies with artworkthat uses social media instagram and conducted in 2016. The exhibits were selected in this study will be limited in ArtJog exhibition. Instagram data collection is done by using meta data search categories based on hashtag.The selection of selfies at the artjog exhibition was done after seeing the rampant selfie at the exhibition also saw the number of uploads with hastag ArtJjog reaching 25,883 and dominated by selfies. Most Selfie actions with artwork and publish on public pages done without mentioning the identity of the artwork and give a new "caption" on the artwork without the permission of the artist.

Comparison between Instagram Data and New Water Quality Index Showing the Level of Activity along the Rivers

Comparison between Instagram Data and New Water Quality Index Showing the Level of Activity along the Rivers

Instagram photos reveal predictive markers of depression

Using Instagram data from 166 individuals, we applied machine learning tools to successfully identify markers of depression. Statistical features were computationally extracted from 43,950 participant Instagram photos, using color analysis, metadata components, and algorithmic face detection. Resulting models outperformed general practitioners’ average unassisted diagnostic success rate for depression. These results held even when the analysis was restricted to posts made before depressed individuals were first diagnosed. Human ratings of photo attributes (happy, sad, etc.) were weaker predictors of depression, and were uncorrelated with computationally-generated features. These results suggest new avenues for early screening and detection of mental illness.

#RIPINSTAGRAM: Examining user’s counter-narratives opposing the introduction of algorithmic personalization on Instagram

When Instagram announced the implementation of algorithmic personalization on their platform a heated debate arose. Several users expressed instantly their strong discontent under the hashtag #RIPINSTAGRAM. In this paper, we examine how users commented on the announcement of Instagram implementing algorithmic personalization. Drawing on the conceptual starting point of framing user comments as “counter-narratives” (Andrews, 2004), which oppose Instagram’s organizational narrative of improving the user experience, the study explores the main concerns users bring forth in greater detail. The two-step analysis draws on altogether 8,645 comments collected from Twitter and Instagram. The collected Twitter data were used to develop preliminary inductive categories describing users’ counter-narratives. Thereafter, we coded all Instagram data extracted from Instagram systematically in order to enhance, adjust and revise the preliminary categories. This inductive coding approach (Mayring, 2000) combined with an in-depth qualitative analysis resulted in the identification of the following four counter-narratives brought forth by users: 1) algorithmic hegemony; 2) violation of user autonomy; 3) prevalence of commercial interests; and 4) deification of mainstream. All of these counter-narratives are related to ongoing public debates regarding the social implications of algorithmic personalization. In conclusion, the paper suggests that the identified counter-narratives tell a story of resistance. While technological advancement is generally welcomed and celebrated, the findings of this study point towards a growing user resistance to algorithmic personalization.

Exploiting Social-Mobile Information for Location Visualization

With a smart phone at hand, it becomes easy now to snap pictures and publish them online with few lines of texts. The GPS coordinates and User-Generated Content (UGC) data embedded in the shared photos provide opportunities to exploit important knowledge to tackle interesting tasks like geographically organizing photos and location visualization. In this work, we propose to organize photos both geographically and semantically, and investigate the problem of location visualization from multiple semantic themes. The novel visualization scheme provides a rich display landscape for geographical exploration from versatile views. A two-level solution is presented, where we first identify the highly photographed places of interest (POI) and discover their focused themes, and then aggregate the lower-level POI themes to generate the higher-level city themes for location visualization. We have conducted experiments on crawled Flickr and Instagram data and exhibited the visualization for the cities of Singapore and Sydney. The experimental results have validated the proposed method and demonstrated the potentials of location visualization from multiple themes.

The Image of a Data City: Studying the Hyperlocal with Social Media

Sharing photos, videos and comments on social media may seem an idle pastime, but it is not without its uses where urban design is concerned. Analysing such posts can yield helpful indicators as to how people experience the built environment. Lev Manovich and Agustin Indaco, of the Software Studies Lab at the University of California, San Diego and the Graduate Center, City University of New York, here outline two of the Lab's recent research projects, which have involved examining extensive Instagram data from various cities around the globe.

What Counts? Reflections on the Multivalence of Social Media Data

Abstract Social media platforms have been characterised by their programmability, affordances, constraints and stakeholders - the question of value and valuation of platforms, their data and features has, however, received less attention in platform studies. This paper explores the specific socio-technical conditions for valuating platform data and suggests that platforms set up their data to become multivalent, that is to be valuable alongside multiple, possibly conflicting value regimes. Drawing on both platform and valuation studies, it asks how the production, storing and circulation of data, its connection to user action and the various stakeholders of platforms contribute to its valuation. Platform data, the paper suggests, is the outcome of capture systems which allow to collapse action and its capture into pre-structured data forms which remain open to divergent interpretations. Platforms offer such grammars of action both to users and other stakeholders in frontand back-ends, inviting them to produce and engage with its data following heterogeneous orders of worth. Platform data can participate in different valuation regimes at the same time - however, the paper concludes, not all actors can participate in all modes of valuation, as in the end, it is the platform that sets the conditions for participation. The paper offers a conceptual perspective to interrogate what data counts by attending to questions of quantification, its entanglement with valuation and the various technologies and stakeholders involved. It finishes with an empirical experiment to map the various ways in which Instagram data is made to count.

Continental-scale quantification of landscape values using social media data

Individuals, communities, and societies ascribe a diverse array of values to landscapes. These values are shaped by the aesthetic, cultural, and recreational benefits and services provided by those landscapes. However, across the globe, processes such as urbanization, agricultural intensification, and abandonment are threatening landscape integrity, altering the personally meaningful connections people have toward specific places. Existing methods used to study landscape values, such as social surveys, are poorly suited to capture dynamic landscape-scale processes across large geographic extents. Social media data, by comparison, can be used to indirectly measure and identify valuable features of landscapes at a regional, continental, and perhaps even worldwide scale. We evaluate the usefulness of different social media platforms-Panoramio, Flickr, and Instagram-and quantify landscape values at a continental scale. We find Panoramio, Flickr, and Instagram data can be used to quantify landscape values, with features of Instagram being especially suitable due to its relatively large population of users and its functional ability of allowing users to attach personally meaningful comments and hashtags to their uploaded images. Although Panoramio, Flickr, and Instagram have different user profiles, our analysis revealed similar patterns of landscape values across Europe across the three platforms. We also found variables describing accessibility, population density, income, mountainous terrain, or proximity to water explained a significant portion of observed variation across data from the different platforms. Social media data can be used to extend our understanding of how and where individuals ascribe value to landscapes across diverse social, political, and ecological boundaries.

Studying Facebook and Instagram data: The Digital Footprints software

The aim of this article is to discuss methodological implications and challenges in different kinds of deep and big data studies of Facebook and Instagram through methods involving the use of Application Programming Interface (API) data. This article describes and discusses Digital Footprints (www.digitalfootprints.dk), a data extraction and analytics software that allows researchers to extract user data from Facebook and Instagram data sources; public streams as well as private data with user consent. Based on insights from the software design process and data driven studies the article argues for three main challenges: Data quality, data access and analysis, and legal and ethical considerations.