Twitter Lists Research Articles

Identifying Domain-specific Opinion Leaders in Twitter (X): An Optimized Approach

The role of opinion leaders on Twitter to analyze and understand the diffusion of information cannot be overlooked. The coming of the information age and the advent of social networking platforms have not eliminated opinion leadership but rather led to the emergence of its new forms. In this line, this paper deals with organically identifying opinion leaders on Twitter, based on the list feature. The method relies on the meta-data of Twitter lists, containing semantic cues to infer the topical expertise of its members. Based on the studies that have already shown the effectiveness of this method, this paper further illustrates in detail how the method can be employed flexibly to identify highly influential Twitter users in any specific domain. In this regard, the method can be adapted to different research questions, allowing researchers to apply it to suit their specific objectives and data. This paper also presents a novel approach as to how influential Twitter users identified through Twitter lists can be ranked. The ranking index proposed is attentive to both vertical (public perception and engagement) and horizontal (peer perception) dimensions of information diffusion.

Mining Twitter lists to extract brand-related associative information for celebrity endorsement

Twitter lists (i.e., curated collections of Twitter accounts) are user-generated and serve primarily as a tool to group other users. Grouping judgments are grounded in the implicit assumption that co-listed members share common associations. As such, Twitter lists are ideal for directly exploring associative links between brands and/or other entities. This research capitalizes on Twitter list membership data to provide a new metric indicating the similarity of users’ list membership profiles. This metric is used as a proxy for perceptions of brand–celebrity (mis)fit (i.e., the degree of congruency or similarity between the celebrity and the brand) in celebrity endorsement situations, where a celebrity's fame or social status is used to promote a brand. To validate the accuracy of the method, we compare the list similarity metric with directly elicited survey data for a test set of 62 celebrities and 64 brands, ranging across eight industry sectors. This research contributes to the extant literature of studies extracting brand-related associative information (i.e., information held in consumers’ memory that contains the meaning of a brand) from large volumes of consumer online data. This research also introduces new ways of data mining to operational research literature and provides managers with a new methodology to directly infer perceptions of brand–celebrity (mis)fit.

Who can verify this? Finding authorities for rumor verification in Twitter

A large body of research work has proposed verification techniques for rumors spreading in social media that mainly relied on subjective evidence, e.g., propagation networks or user interactions. Alternatively, in this work, we introduce the task of authority finding in social media, in which we aim to find authorities, for given rumors spreading specifically in Twitter, who can help verify them by providing exclusive/convincing evidence that supports or denies those rumors. We release the first test collection for Authority FINding in Arabic Twitter (AuFIN). The collection comprises 150 rumors (expressed in tweets) associated with a total of 1,044 authority accounts and a user collection of 395,231 Twitter accounts (members of 1,192,284 unique Twitter lists). Moreover, we propose a hybrid model that employs pre-trained language models and combines lexical, semantic, and network signals to find authorities. Our experiments show that the textual representation of users is insufficient, and incorporating the Twitter network features improved the recall of authorities by 34%. Moreover, semantic ranking is inferior to the lexical and network-based ranking in terms of precision, but superior in terms of recall. Therefore, combining both the semantic and network-based ranking achieved the best overall performance achieving a precision of 0.413 and 0.213 at depth 1 and 5 respectively. We show that rumor expansion by exploiting Knowledge Bases improves the recall of authorities by up to 15%. Furthermore, we find that SOTA models for topic expert finding perform poorly on finding authorities. Finally, drawing upon our experiments, we discuss failure factors and make recommendations for future research directions in addressing this task.

A text mining analysis of human flourishing on Twitter

The power of social media in spreading the idea of wellbeing has already been addressed by several psychologists and scholars through the analysis of the vocabulary; however, the use of the human flourishing (HF) concept in such platforms has not yet been analyzed. This study addresses such a topic by analyzing more than 600 thousand Twitter messages posted by a community of users who associate themselves with HF and comparing them to more than 400 thousand messages in other Twitter lists. The study aims to identify the HF users’ interests, the richness in their vocabulary, the feelings and emotions that they share, and the grammar used in their constructions. Such an analysis was conducted through text mining computational methods, including sentiment analysis, natural language processing (NLP), and topic modeling. The results revealed that although HF users employ average vocabulary diversity, they share more positive emotions, and a greater variety of emojis. They also tended to discuss different topics, from more spiritual and health-related subjects to more practical matters related to work and success. Finally, they generally wrote from an empathetic state of mind, caring about people’s day-to-day feelings and about the world.

EDITORIAL COMMENT

In this mixed-methods study, Friedman et al. evaluate the role and applicant perception of Twitter in the first virtual urology residency match cycle. Quantitative and qualitative data were obtained from 3 sources: a public Twitter list commonly used by urology applicants, online applicant survey, and semi-structured phone interviews with author-selected applicants with an active Twitter presence. The authors identified 245 applicant Twitter accounts (50.9% of total applicants), whereby matched applicants were more likely to have Twitter accounts (59% vs 28%, P = .002).

Personalized Mobile App Recommendation by Learning User’s Interest from Social Media

Abstract: In social media, user interests and knowledge are vital but often overlooked resources. There are a few ways to get a sense of what people are known for, such as Twitter lists and LinkedIn Skill Tags, but most people are untagged, so their interests and expertise are effectively hidden from applications like personalised recommendation and community detection and expert mining. We obtain personalised app recommendations by learning the interest's association between applications and tweets by introducing an unique generative model called IMCF+ to convert user interest from rich tweet information to sparse app usage. We analyse the performance of this technique predicts the top ten apps with an 82.5 percent success rate using only 10% training data. Furthermore, in the high sparsity situation and user cold-start scenario, this purpose technique outperforms the other six state-of-the-art algorithms by 4.7 percent and 10%, demonstrating the effectiveness of our technology. All of these findings show that our method can reliably extract user interests from tweets in order to aid in the solution of the personalised app recommendation problem. Keywords: Social Media, User Profile, deep learning, Privacy, matrix factorization,App recommendation.

Patterns in Interactive Tagging Networks

How do users behave if they can tag each other in social networks?In this paper, we answer this question by studying the interactive tagging network constructed by Twitter lists. Twitter lists can be regarded as the tagging process; a user (i.e., tagger) creates a list with a name (i.e., tag) and adds other users (i.e., tagged users) into the list. This tagging network is by nature different from the resource tagging networks (e.g., Flickr and Delicious) because users on this network can tag each other. We address the following research questions: (RQ1) What is the common patterns and the difference between the interactive tagging network and the resource tagging networks? (RQ2) Do users tag each other on the interactive tagging network? And if so, to what extent? (RQ3) What is the difference between the two types of relationships on Twitter: who-tags-whom and who-follows-whom? By quantitatively studying million-scale networks, we found the pervasive patterns across the different tagging networks, and the interactive patterns within the interactive tagging network. This study sheds light on the underlying characteristics of the interactive tagging network, which is relevant to the social scientists and the system designers of the tagging systems.

Influence propagation: Interest groups and node ranking models

Influence propagation is studied in various contexts with significant practical potential applications such as viral marketing, monitoring people opinions, social psychology analysis and communities discovery. All the previously mentioned applications are concerned about the role played by the user in social network and his/her effect on other users. The current literature lacks approaches that identify influential users in social networks and analyze users ranking with respect to the users interactivity to the disseminated content.The main contribution of this work is to achieve users ranking based on influence propagation in social networks. In order to achieve this goal, two models are proposed. The first model captures interest groups regarding specific disseminated content. The second model is a novel influence propagation model that ranks users in each interest group based on their role in spreading content. Moreover, this model introduces the new concept of ”ultimate observers” to adjust the rank of influential users in each group. Finally, we perform extensive experiments on real datasets to demonstrate the relevance of the proposed models.Both models are evaluated in experimental setup using the following benchmark datasets: Highschool, Email-Eu-core, US Airports, Advogato Trust and Twitter Lists networks. The proposed models are assessed in respect of the accurate separation of interest groups, distinction, uniqueness and effectiveness of nodes ranking.Experiments show that the proposed models have promising results in detecting the interest groups and ranking users in terms of their influence propagation.

Black Books and Dead Black Bodies: Twitter, Hashtags, and Antiracist Reading Lists

Black Books and Dead Black Bodies: Twitter, Hashtags, and Antiracist Reading Lists

Using a Digital Personal Learning Network Assignment to Teach Social Curation and Lifelong Learning in Marketing

As the use of social media continues to grow in practice and as an academic discipline, so too does the need for marketing students (and faculty) to develop and maintain a career-focused and current knowledge warehouse of information that is optimized to their own unique life situation—hence, the creation and use of what is described as a digital personal learning network or “PLN.” This article describes a proven assignment framework, requiring students to build their own digital PLN, using widely available RSS newsfeed tools such as Feedly and Twitter Lists. Student feedback is offered to support the effectiveness of this approach and suggestions are made regarding other courses that could benefit from being taught with the support of a PLN-based assignment.

Stroke Survivors on Twitter: Sentiment and Topic Analysis From a Gender Perspective.

BackgroundStroke is the worldwide leading cause of long-term disabilities. Women experience more activity limitations, worse health-related quality of life, and more poststroke depression than men. Twitter is increasingly used by individuals to broadcast their day-to-day happenings, providing unobtrusive access to samples of spontaneously expressed opinions on all types of topics and emotions.ObjectiveThis study aimed to consider the raw frequencies of words in the collection of tweets posted by a sample of stroke survivors and to compare the posts by gender of the survivor for 8 basic emotions (anger, fear, anticipation, surprise, joy, sadness, trust and disgust); determine the proportion of each emotion in the collection of tweets and statistically compare each of them by gender of the survivor; extract the main topics (represented as sets of words) that occur in the collection of tweets, relative to each gender; and assign happiness scores to tweets and topics (using a well-established tool) and compare them by gender of the survivor.MethodsWe performed sentiment analysis based on a state-of-the-art lexicon (National Research Council) with syuzhet R package. The emotion scores for men and women were first subjected to an F-test and then to a Wilcoxon rank sum test. We extended the emotional analysis, assigning happiness scores with the hedonometer (a tool specifically designed considering Twitter inputs). We calculated daily happiness average scores for all tweets. We created a term map for an exploratory clustering analysis using VosViewer software. We performed structural topic modelling with stm R package, allowing us to identify main topics by gender. We assigned happiness scores to all the words defining the main identified topics and compared them by gender.ResultsWe analyzed 800,424 tweets posted from August 1, 2007 to December 1, 2018, by 479 stroke survivors: Women (n=244) posted 396,898 tweets, and men (n=235) posted 403,526 tweets. The stroke survivor condition and gender as well as membership in at least 3 stroke-specific Twitter lists of active users were manually verified for all 479 participants. Their total number of tweets since 2007 was 5,257,433; therefore, we analyzed the most recent 15.2% of all their tweets. Positive emotions (anticipation, trust, and joy) were significantly higher (P<.001) in women, while negative emotions (disgust, fear, and sadness) were significantly higher (P<.001) in men in the analysis of raw frequencies and proportion of emotions. Happiness mean scores throughout the considered period show higher levels of happiness in women. We calculated the top 20 topics (with percentages and CIs) more likely addressed by gender and found that women’s topics show higher levels of happiness scores.ConclusionsWe applied two different approaches—the Plutchik model and hedonometer tool—to a sample of stroke survivors’ tweets. We conclude that women express positive emotions and happiness much more than men.

Misinformation-oriented expert finding in social networks

Due to the distributed and decentralized nature of social media, respective content that contains misinformation is usually propagated without any type of moderation, which may mislead the public and have a profound real-world impact. In addition, it is quite challenging to distinguish misinformation with high precision, since the content is often short and lacks of semantics. A promising solution is to utilize the crowdsourcing wisdom that pushes the suspected misinformation to relevant users based on the expertise and collects the assessments to judge the credibility. Even though a lot of expert finding models have been employed, however, these methods cannot effectively deal with the misinformation-oriented expert matching tasks since the data collected from social network is different form traditional text collection. To this end, we focus on how to obtain an appropriate matching between the suspect misinformation and corresponding experts, and propose a multi-topic expert finding method, called LTM (List based Topic Model), to sufficiently utilize crowdsourcing wisdom. Moreover, we optimize the query results with the help of supervised information that extracted from Twitter Lists. Finally, we demonstrate the effectiveness of our work with experiments on real-world data and verify the superiority of our proposed model in accuracy.

Tweeting into the void?: creating a UK library Twitter list and analyzing best practice – successes and myths

Despite the vast amount of research into social media use by libraries, no research has been made into its use by smaller UK libraries. Although many statements have been made regarding the time- and cost-saving nature of social media, there is a lack of comparative research about its usefulness in different types of library. To address these points, this study gathered statistics from 1,425 library accounts on the social media tool Twitter. Five smaller libraries were selected for a more in-depth metric analysis and interview regarding their accounts and their measuring of return on investment (ROI). The study found that while many libraries are using Twitter, academic libraries were the first to sign up en masse. Despite clear best practice criteria, many accounts are not utilizing Twitter to its fullest capacity. The two greatest influencing factors on followers were found to be the amount of time since the account’s registration and the type of library. When interviewed, the smaller libraries in this study were shown to be following best practice criteria, but were working outside these parameters to create unique initiatives. However, the five interviewed libraries have not been recording any metrics, data or examples of successful tweets on social media, making it difficult to measure ROI. Furthermore, the libraries interviewed have been reaching followers who are not library users. This alters libraries’ social media strategies and is something that should be part of the discussion surrounding library use of social media.

SMS: A Framework for Service Discovery by Incorporating Social Media Information

With the explosive growth of services, including Web services, cloud services, APIs and mashups, discovering the appropriate services for consumers is becoming an imperative issue. The traditional service discovery approaches mainly face two challenges: 1) the single source of description documents limits the effectiveness of discovery due to the insufficiency of semantic information; 2) more factors should be considered with the generally increasing functional and nonfunctional requirements of consumers. In this paper, we propose a novel framework, called SMS, for effectively discovering the appropriate services by incorporating social media information. Specifically, we present different methods to measure four social factors (semantic similarity, popularity, activity, decay factor) collected from Twitter. Latent Semantic Indexing (LSI) model is applied to mine semantic information of services from meta-data of Twitter Lists that contains them. In addition, we assume the target query-service matching function as a linear combination of multiple social factors and design a weight learning algorithm to learn an optimal combination of the measured social factors. Comprehensive experiments based on a real-world dataset crawled from Twitter demonstrate the effectiveness of the proposed framework SMS, through some compared approaches.

Finding Topic Experts in the Twitter Dataset Using LDA Algorithm

In microblogging services like Twitter, the expert judgment problem has gained increasing attention in social media. Twitter is a new type of social media that provides a publicly available way for users to publish 140-character short messages (tweets). However, previous methods cannot be directly applied to twitter experts finding problems. They generally rely on the assumption that all the documents associated with the candidate experts contain tacit knowledge related to the expertise of individuals. Whereas it might not be directly associated with their expertise, i.e., who is not an expert, but may publish/re-tweet a substantial number of tweets containing the topic words. Recently, several attempts use the relations among users and twitter list for expert finding. Nevertheless, these strategies only partially utilize such relations. To address these issues a probabilistic method is developed to jointly exploit three types of relations (i.e., follower relation, user-list relation and list-list relation) for finding experts. LDA algorithms are used for finding topic experts. LDA is based upon the concept of searching for a linear combination of variables (predictors) that best separates two classes (targets). Semi-supervised graph-based ranking approach (SSGR) to offline calculate the global authority of users. Then, the local relevance between users and the given query is computed. Then, the rank of all the users is found and the top-N users with the highest-ranking scores. Therefore, the proposed approach can jointly exploit the different types of relations among users and lists for improving the accuracy of finding experts on a given topic on Twitter.

Location-Sensitive User Profiling Using Crowdsourced Labels

In this paper, we investigate the impact of spatial variation on the construction of location-sensitive user profiles. We demonstrate evidence of spatial variation over a collection of Twitter Lists, wherein we find that crowdsourced labels are constrained by distance. For example, that energy in San Francisco is more associated with the green movement, whereas in Houston it is more associated with oil and gas. We propose a three-step framework for location-sensitive user profiling: first, it constructs a crowdsourced label similarity graph, where each labeler and labelee are annotated with a geographic coordinate; second, it transforms this similarity graph into a directed weighted tree that imposes a hierarchical structure over these labels; third, it embeds this location-sensitive folksonomy into a user profile ranking algorithm that outputs a ranked list of candidate labels for a partially observed user profile. Through extensive experiments over a Twitter list dataset, we demonstrate the effectiveness of this location-sensitive user profiling.

An Integrated Approach for Identifying Topical Experts in Microblogs

In the recent times, usage of Social Networking and Micro-blogging sites by the people has increased exponentially. Identifying the right topical experts in a particular domain is a tedious task as huge amount of data being processed. The existing approaches limited in accuracy, which leads to providing irrelevant results. Furthermore, few deal with syntactic similarity and not the semantic analysis. In this paper, we introduce an integrated approach which combines focus crawling, semantic analysis and personalized page ranking algorithm to provide top-k ranked results for a topic. Twitter data is taken as input and the twitter lists are extracted to construct the endorsement graph. Links in the graph are weighted using personalized PageRank. Since social network itself has a huge chunk of data, it is obvious for the endorsement graph to have quite large number of nodes. To increase the scalability and performance, focused crawling is applied before the PageRank calculation. The semantic similarity is calculated between the given input query and the Twitter list name/description to yield better results. We compare the results with Twitter’s WTF (Who To Follow) algorithm to showcase that the proposed system provides more obvious and serendipitous topical experts.

Mining half a billion topical experts across multiple social networks

Mining topical experts on social media is a problem that has gained significant attention due to its wide-ranging applications. Here we present the first study that combines data from four major social networks -- Twitter, Facebook, Google+ and LinkedIn, along with the Wikipedia graph and internet webpage text and metadata, to rank topical experts across the global population of users. We perform an in-depth analysis of 37 features derived from various data sources such as message text, user lists, webpages, social graphs and wikipedia. This large-scale study includes more than 12 billion messages over a 90-day sliding window and 58 billion social graph edges. Comparison reveals that features derived from Twitter Lists, Wikipedia, internet webpages and Twitter Followers are especially good indicators of expertise. We train an expertise ranking model using these features on a large ground truth dataset containing almost 90,000 labels. This model is applied within a production system that ranks over 650 million experts in more than 9,000 topical domains on a daily basis. We provide results and examples on the effectiveness of our expert ranking system, along with empirical validation. Finally, we make the topical expertise data available through open REST APIs for wider use.

Learning to Find Topic Experts in Twitter via Different Relations

Expert finding has become a hot topic along with the flourishing of social networks, such as micro-blogging services like Twitter. Finding experts in <i>Twitter</i> is an important problem because tweets from experts are valuable sources that carry rich information (e.g., trends) in various domains. However, previous methods cannot be directly applied to <i>Twitter</i> expert finding problem. Recently, several attempts use the relations among users and <i>Twitter List</i> s for expert finding. Nevertheless, these approaches only partially utilize such relations. To this end, we develop a probabilistic method to jointly exploit three types of relations (i.e., <i>follower</i> relation, <i>user-list</i> relation, and <i>list-list</i> relation) for finding experts. Specifically, we propose a <i>S</i> emi- <i>S</i> upervised <i>G</i> raph-based <i>R</i> anking approach ( <inline-formula><tex-math notation="LaTeX">$\sf{SSGR}$</tex-math></inline-formula> ) to offline calculate the <i>global authority</i> of users. In <inline-formula><tex-math notation="LaTeX">$\sf{SSGR}$</tex-math></inline-formula> , we employ a normalized Laplacian regularization term to jointly explore the three relations, which is subject to the supervised information derived from Twitter crowds. We then online compute the <i>local relevance</i> between users and the given query. By leveraging the <i>global authority</i> and <i>local relevance</i> of users, we rank all of users and find top-N users with highest ranking scores. Experiments on real-world data demonstrate the effectiveness of our proposed approach for <i>topic-specific</i> expert finding in <i>Twitter</i> .

Training a text classifier with a single word using Twitter Lists and domain adaptation

Annotating data is a common bottleneck in building text classifiers. This is particularly problematic in social media domains, where data drift requires frequent retraining to maintain high accuracy. In this paper, we propose and evaluate a text classification method for Twitter data whose only required human input is a single keyword per class. The algorithm proceeds by identifying exemplar Twitter accounts that are representative of each class by analyzing Twitter Lists (human-curated collections of related Twitter accounts). A classifier is then fit to the exemplar accounts and used to predict labels of new tweets and users. We develop domain adaptation methods to address the noise and selection bias inherent to this approach, which we find to be critical to classification accuracy. Across a diverse set of tasks (topic, gender, and political affiliation classification), we find that the resulting classifier is competitive with a fully supervised baseline, achieving superior accuracy on four of six datasets despite using no manually labeled data.