Tweet Metadata Research Articles

A twitter analysis of patient and family experience in pediatric spine surgery.

There is little data on patient and caregiver perceptions of spine surgery in children and youth. This study aims to characterize the personal experiences of patients, caregivers, and family members surrounding pediatric spine surgery through a qualitative and quantitative social media analysis. The Twitter application programming interface was searched for keywords related to pediatric spine surgery from inception to March 2022. Relevant tweets and accounts were extracted and subsequently classified using thematic labels. Tweet metadata was collected to measure user engagement via multivariable regression. Sentiment analysis using Natural Language Processing was performed on all tweets with a focus on tweets discussing the personal experiences of patients and caregivers. 2424 tweets from 1847 individual accounts were retrieved for analysis. Patients and caregivers represented 1459 (79.0%) of all accounts. Posts discussed the personal experiences of patients and caregivers in 83.5% of tweets. Pediatric spine surgery research was discussed in few posts (n=90, 3.7%). Within the personal experience category, 975 (48.17%) tweets were positive, 516 (25.49%) were negative, and 533 (26.34%) were neutral. Presence of a tag (beta: -6.1, 95% CI -9.7 to -2.5) and baseline follower count (beta<0.001, 95% CI <0.001 to <0.001) significantly affected tweet engagement negatively and positively, respectively. Patients and caregivers actively discuss topics related to pediatric spine surgery on Twitter. Posts discussing personal experience are most prevalent, while posts on research are scarce, unlike previous social media studies. Pediatric spine surgeons can leverage this dialogue to better understand the worries and needs of patients and their families.

Ridge count thresholding to uncover coordinated networks during onset of the Covid-19 pandemic.

In order to combat information operations (IO) and disinformation campaigns, one must look at the behaviors of the accounts pushing specific narratives and stories through social media, not at the content itself. In this work, we present a new process for extracting tweet storms and uncovering networks of accounts that are working in a coordinated fashion using ridge count thresholding (RCT). To do this, we started with a dataset of 60 million individual tweets from the early weeks of the Covid-19 pandemic. Coherent topics are extracted from this data by testing three different preprocessing pipelines and applying Orthogonal Nonnegative Matrix Factorization (ONMF). The most effective preprocessing pipeline used hashtag preclustering to downselect the total dataset to the 7 million tweets that included the top hashtags. Each topic identified by ONMF is described by a topic-tweet signal, crafted using the time stamp included in each tweet’s metadata. These signals were broken down into tweet storms using RCT, which is calculated from the Dynamic Wavelet Fingerprint transform of each topic-tweet signal. Each tweet storm described a time of increased activity around a topic. Tweet storms identified in this way each represent some behavior in the underlying network. In total, we identified 39,817 total tweet storms that included about 2 million unique tweets. These tweet storms were used to identify networks of accounts that commonly co-occur within tweet storms to isolate those communities most responsible for driving narratives and pushing stories through social media. Through this process, we were able to identify 22 unique networks of accounts that were densely connected based on RCT tweet storm identification. Many of the identified networks exhibit obvious inauthentic behaviors that are potentially a part of an IO campaign.

Safe deliberative spaces online between refugee-claimants and the international community: Rohingya refugee use of Twitter for advocacy and deliberation

According to the United Nations, the world’s most discriminated-against population is the Rohingya, an ethnic Muslim minority from Myanmar who have been denied citizenship in their country. Today, they are largely displaced internally or residing in one of two camps in the region of Cox Bazar, Bangladesh. In order to advocate for their cause in terms of human rights and humanitarian needs, some Rohingya have turned to Twitter. This paper analyses tweets collected in August 2021 about the Rohingya cause, to understand the deliberative potential of this platform for refugee-claimants. It uses tweet metadata analysis, such as hashtag and mention analysis, along with LDA topic analysis, to analyse deliberative quality in the data. In this paper, we find that the tweets are mainly used for advocacy and have both low levels of polarisation and high levels of homogeneity. These findings diverge from analyses of other social media platforms, such as Facebook, which has been used partly for spreading hate-speech related to the Rohingya. We conclude that the Twitter platform is currently being used as an effective deliberative space between the Rohingya and the international humanitarian and human rights community, especially when it comes to advocacy.

LOOK WHO’S TALKING: USING HUMAN CODING TO ESTABLISH A MACHINE LEARNING APPROACH TO TWITTER EDUCATION CHATS

Twitter has become a hub for many different types of educational conversations, denoted by hashtags and organized by a variety of affinities. Researchers have described these educational conversations on Twitter as sites for teacher professional development. Here, we studied #Edchat—one of the oldest and busiest Twitter educational hashtags—to examine the content of contributions for evidence of professional purposes. We collected tweets containing the text “#edchat” from October 1, 2017 to June 5, 2018, resulting in a dataset of 1,228,506 unique tweets from 196,263 different contributors. Through initial human-coded content analysis, we sorted a stratified random sample of 1,000 tweets into four inductive categories: tweets demonstrating evidence of different professional purposes related to (a) self, (b) others, (c) mutual engagement, and (d) everything else. We found 65% of the tweets in our #Edchat sample demonstrated purposes related to others, 25% demonstrated purposes related to self, and 4% of tweets demonstrated purposes related to mutual engagement. Our initial method was too time intensive—it would be untenable to collect tweets from 339 known Twitter education hashtags and conduct human-coded content analysis of each. Therefore, we are developing a scalable machine-learning model—a multiclass logistic regression classifier using an input matrix of features such as tweet types, keywords, sentiment, word count, hashtags, hyperlinks, and tweet metadata. The anticipated product of this research—a successful, generalizable machine learning model—would help educators and researchers quickly evaluate Twitter educational hashtags to determine where they might want to engage.

On the use of distributed semantics of tweet metadata for user age prediction

Social media data represent an important resource for behavioral analysis of the aging population. This paper addresses the problem of age prediction from Twitter dataset, where the prediction issue is viewed as a classification task. For this purpose, an innovative model based on Convolutional Neural Network is devised. To this end, we rely on language-related features and social media specific metadata. More specifically, we introduce two features that have not been previously considered in the literature: the content of URLs and hashtags appearing in tweets. We also employ distributed representations of words and phrases present in tweets, hashtags and URLs, pre-trained on appropriate corpora in order to exploit their semantic information in age prediction. We show that our CNN-based classifier, when compared with baseline models, yields an improvement of up to 12.3% for Dutch dataset, 9.8% for English1 dataset, and 6.6% for English2 dataset in the micro-averaged F1 score.

An Analytical Model for Identifying Suspected Users on Twitter

With the use of identity resolution, both information leakage and identity hacking can be reduced to some extent. In this paper, a prototype has been developed to classify Twitter users as suspicious and nonsuspicious on the basis of features which identify user demographics and their tweeting activity using Twitter APIs. A model has been devised based upon user and tweet meta-data which is used to calculate user score and tweet score, and further aggregate the values generated by these scores to label suspicious and nonsuspicious users in the collected dataset of around 21,492 Twitter users. Further, support vector machine classifier has been used to classify the labeled data. Through this paper, our analysis about the role of features and the characteristics of dataset used for the categorization of users in Twitter has been reported. The experimental results illustrate that the proposed system can identify suspicious users with an accuracy of 94.1%.

A Large-scale Behavioural Analysis of Bots and Humans on Twitter

Recent research has shown a substantial active presence of bots in online social networks (OSNs). In this article, we perform a comparative analysis of the usage and impact of bots and humans on Twitter—one of the largest OSNs in the world. We collect a large-scale Twitter dataset and define various metrics based on tweet metadata. Using a human annotation task, we assign “bot” and “human” ground-truth labels to the dataset and compare the annotations against an online bot detection tool for evaluation. We then ask a series of questions to discern important behavioural characteristics of bots and humans using metrics within and among four popularity groups. From the comparative analysis, we draw clear differences and interesting similarities between the two entities.

Prediction of drive-by download attacks on Twitter

The popularity of Twitter for information discovery, coupled with the automatic shortening of URLs to save space, given the 140 character limit, provides cybercriminals with an opportunity to obfuscate the URL of a malicious Web page within a tweet. Once the URL is obfuscated, the cybercriminal can lure a user to click on it with enticing text and images before carrying out a cyber attack using a malicious Web server. This is known as a drive-by download. In a drive-by download a user's computer system is infected while interacting with the malicious endpoint, often without them being made aware the attack has taken place. An attacker can gain control of the system by exploiting unpatched system vulnerabilities and this form of attack currently represents one of the most common methods employed. In this paper we build a machine learning model using machine activity data and tweet metadata to move beyond post-execution classification of such URLs as malicious, to predict a URL will be malicious with 0.99 F-measure (using 10-fold cross-validation) and 0.833 (using an unseen test set) at 1 s into the interaction with the URL. Thus, providing a basis from which to kill the connection to the server before an attack has completed and proactively blocking and preventing an attack, rather than reacting and repairing at a later date.

Prevalence of Marijuana-Related Traffic on Twitter, 2012-2013: A Content Analysis.

This study assessed marijuana-related content posted by adolescents on Twitter and examined content variation before and after the 2012 U.S. election legalizing recreational use in two states. For two 3-week periods occurring 6 months before and after the election, a 1% random sample was obtained of all tweets matching a set of marijuana-related queries. Original content was separated from reposted content (retweets), and foreign language tweets and those not related to marijuana were excluded. Using a structured codebook, tweet content was categorized (e.g., mention of personal marijuana use, parents' views, perceived effects.) Self-reported age was extracted from tweet metadata when available. Chi-square tests were used to assess differences in content by whether the user self-identified as an adolescent and to compare content pre- versus post-election. The full sample consisted of 71,901 tweets. After excluding nonrelevant tweets and separating original tweets from retweets, the analytic sample included 36,969 original tweets. A majority (65.6%) of original tweets by adolescents (n=1,928) reflected a positive attitude toward marijuana, and 42.9% indicated personal use. Of adolescents' tweets that mentioned parents, 36.0% of tweets indicated parental support for the adolescent's marijuana use. Tweets about personal marijuana use increased from 2012 to 2013, as did positive perceptions about the drug. Adolescents and others on Twitter are exposed to positive discussion normalizing use. Over the study period, Twitter was increasingly used to disclose marijuana use.