Search results

The purpose of this paper is to understand the similarities and differences between the Twitter users who tweeted on journal articles in psychology and political science disciplines.

The data were collected from Web of Science, Altmetric.com, and Twitter. A total of 91,826 tweets with 22,541 distinct Twitter user profiles for psychology discipline and 29,958 tweets with 10,478 distinct Twitter user profiles for political science discipline were used for analysis. The demographics analysis includes gender, geographic location, individual or organization user, academic or non-academic background, and psychology/political science domain knowledge background. A machine learning approach using support vector machine (SVM) was used for user classification based on the Twitter user profile information. Latent Dirichlet allocation (LDA) topic modeling was used to discover the topics that the users discussed from the tweets.

Results showed that the demographics of Twitter users who tweeted on psychology and political science are significantly different. Tweets on journal articles in psychology reflected more the impact of scientific research finding on the general public and attracted more attention from the general public than the ones in political science. Disciplinary difference in term of user demographics exists, and thus it is important to take the discipline into consideration for future altmetrics studies.

From this study, researchers or research organizations may have a better idea on who their audiences are, and hence more effective strategies can be taken by researchers or organizations to reach a wider audience and enhance their influence.

The study aimed to examine how different communities concerned with dementia engage and interact on Twitter.

A dataset was sampled from 8,400 user profile descriptions, which was labelled into five categories and subjected to multiple machine learning (ML) classification experiments based on text features to classify user categories. Social network analysis (SNA) was used to identify influential communities via graph-based metrics on user categories. The relationship between bot score and network metrics in these groups was also explored.

Classification accuracy values were achieved at 82% using support vector machine (SVM). The SNA revealed influential behaviour on both the category and node levels. About 2.19% suspected social bots contributed to the coronavirus disease 2019 (COVID-19) dementia discussions in different communities.

The study is a unique attempt to apply SNA to examine the most influential groups of Twitter users in the dementia community. The findings also highlight the capability of ML methods for efficient multi-category classification in a crisis, considering the fast-paced generation of data.

The peer review history for this article is available at: https://publons.com/publon/10.1108/OIR-04-2021-0208.

This work studies automated user classification on Twitter in the public health domain, a task that is essential to many public health-related research works on social media but has not been addressed. The purpose of this paper is to obtain empirical knowledge on how to optimise the classifier performance on this task.

A sample of 3,100 Twitter users who tweeted about different health conditions were manually coded into six most common stakeholders. The authors propose new, simple features extracted from the short Twitter profiles of these users, and compare a large set of classification models (including state-of-the-art) that use more complex features and with different algorithms on this data set.

The authors show that user classification in the public health domain is a very challenging task, as the best result the authors can obtain on this data set is only 59 per cent in terms of F1 score. Compared to state-of-the-art, the methods can obtain significantly better (10 percentage points in F1 on a “best-against-best” basis) results when using only a small set of 40 features extracted from the short Twitter user profile texts.

The work is the first to study the different types of users that engage in health-related communication on social media, applicable to a broad range of health conditions rather than specific ones studied in the previous work. The methods are implemented as open source tools, and together with data, are the first of this kind. The authors believe these will encourage future research to further improve this important task.

The purpose of this study is to figure out the visiting behaviors of the users who have different characteristics on Twitter.

The visit history of users who share their Foursquare check-ins on Twitter and the characteristics of visited venues (category, check-in count, tip count, like count, rating, and price tier) was collected with Foursquare API. In addition, the number of followers, friends, tweets and favorite-count were collected via Twitter API. First, users were clustered according to their Twitter related attributes. After that, profiling was applied on clusters according to the characteristics of the venues that were visited by the users.

Clustering analysis generated three clusters, namely, ordinary, talkative and popular. For each cluster, the visited venues were investigated according to the price classification, check-in, like, tip counts and the categories. The users in ordinary class prefer cheaper venues rather than talkative and popular users. On the other hand, popular users prefer the venues with the highest average number of check-ins, likes and tip counts. The top two categories for all clusters are cafe and shopping mall.

This study differentiates from the other studies in the literature by examining the data from Twitter with clustering and profiling these clusters with Foursquare data to understand venue preferences of Twitter users having various characteristics. The findings of this study will provide new insights for business owners to understand the customers more comprehensively and design better marketing strategies.

The purpose of this study is to understand the use of social networking sites (SNSs) by hotels. Specifically, drawn upon a resource and capability-based perspective, this study addresses two research questions: (1) the relationship between a hotel’s resources and its use of Twitter and (2) the relationship between the use of Twitter by hotels and their RevPAR.

The research data include the hotel chain scales, Twitter user profiles and Twitter activities of the hotel parent companies in the USA and the hotels’ RevPAR. To more clearly understand the effect of the use of SNSs, the study uses two dimensions: electronic word-of-mouth and customer engagement. The two dimensions of the hotels’ Twitter use are calculated based on the data extracted from their Twitter user profiles and historical tweets. For a practical purpose, a social media index (SMI), which combines electronic word-of-mouth and the customer engagement score, was used to determine the overall level of Twitter use by hotels.

For RQ1, the results indicate there is a positive association between a hotel’s resources and Twitter use. For RQ2, this study shows there is also a positive association between Twitter use by hotels and their RevPAR.

Twitter use appears to be associated with hotels’ resources. In turn, Twitter use is positively associated with hotel RevPAR. Thus, hotels should look at Twitter as a potential strategic tool for business operation and attempt to increase their ability to leverage Twitter (and other SNSs) for organizational goals (e.g. sales, promotion, customer service).

To the authors’ knowledge, this is the first study empirically investigating the use of SNSs by hotels with the data drawn from actual firm-generated content (e.g. tweets, retweets) and hotels’ user profile information from Twitter.

The purpose of this study is to facilitate the task of finding appropriate information to read about, and searching for people who are in the same field of interest. Knowing that more people keep up with new streaming information on Twitter micro-blogging service. With the immense number of micro-posts shared via the follower/followee network graph, Twitter users find themselves in front of millions of tweets, which makes the task crucial.

In this paper, a long short–term memory (LSTM) model that relies on the latent Dirichlet allocation (LDA) output vector for followee recommendation, the LDA model applied as a topic modeling strategy is proposed.

This study trains the model using a real-life data set extracted based on Twitter follower/followee architecture. It confirms the effectiveness and scalability of the proposed approach. The approach improves the state-of-the-art models average-LSTM and time-LSTM.

This study improves mainly the existing followee recommendation systems. Because, unlike previous studies, it applied a non-hand-crafted method which is the LSTM neural network with LDA model for topics extraction. The main limitation of this study is the cold-start users cannot be treated, also some active fake accounts may not be detected.

The aim of this approach is to assist users seeking appropriate information to read about, by choosing appropriate profiles to follow.

This approach consolidates the social relationship between users in a microblogging platform by suggesting like-minded people to each other. Thus, finding users with the same interests will be easy without spending a lot of time seeking relevant users.

Instead of classic recommendation models, the paper provides an efficient neural network searching method to make it easier to find appropriate users to follow. Therefore, affording an effective followee recommendation system.

The purpose of this paper is to provide a network analysis of Twitter discussions about Myung-Bak Lee, a former president of South Korea, to gain a better understanding of the dynamics of the public opinion exchange on Twitter.

Opinion leaders in the discussion network were identified by considering the longitudinal distribution of tweets containing the former president’s name, and three types of messages (“followings,” “mentions,” and “retweets”) were analyzed using data collected from November 1, 2011, to April 20, 2012. The sample included 26,150 Twitter users and 892,034 relationships reflecting three types of messages.

The results indicate that the discussion about President Myung-Bak Lee was dominated by liberal Twitter users who already had considerable influence both online and offline. In addition, Twitter users were unlikely to interact with other users with opposing political views.

Almost all of the opinion leaders identified in the study held liberal political views, and liberal Twitter users dominated the discussion network. In addition, the Korean Twitter network showed the presence of the homophily phenomenon, implying that opinion leaders’ influence within the Twitter network was limited to other users sharing the same political views. Further, political views of opinion leaders were skewed toward a particular political stance without necessarily representing the opinion of the general public, possibly hindering the democratic process.

This study tests the homophily thesis in the context of Twitter users in Korea and contributes to the literature on Twitter-based political discourse by identifying opinion leaders in Korean Twitter networks and examining the phenomenon of homophily within those networks.

Social media is noted for its usefulness and contribution to destination marketing and management. Social media data is particularly valued as a source to understand issues such as tourist behavior and destination marketing strategies. Among the social media platforms, Twitter is one of the most utilized in research. Its use raises two issues: the challenge of obtaining historical data and the importance of qualitative data analysis. Regarding these issues, the chapter argues that retrieving tweets using hashtags and keywords on the Twitter website provides a corpus of tweets that is valuable for research, especially for qualitative inquiries. In addition, the value of qualitative analysis of Twitter data is presented, demonstrating, among other things, how such an approach captures in-depth information, enables appreciation and inclusion of the nonconventional language used on social media, distinguishes between “noise” and useful information, and recognizes information as the sum of all parts in the data.

Owing to the large amount of information available on Twitter (a micro blogging service) that is not necessarily true or believable, credibility of news published in such an electronic channel has become an important area for investigation in the field of web credibility. This paper aims to address this issue.

A system was developed to measure the credibility of news content published in Twitter. The system uses two approaches to assign credibility levels (low, high and average) to each tweet. The first approach is based on the similarity between Twitter posts (tweets) and authentic (i.e. verified) news sources. The second approach is based on the similarity with verified news sources in addition to a set of proposed features.

The evaluations of the two approaches showed that assigning credibility levels to Twitter tweets for the first approach has a higher precision and recall. Additional experiments showed that the linking feature has its impact on the second approach results.

The proposed system is experimental; thus further experiments are needed to prove these findings.

This paper contributes to the research on web credibility. It is believed to be the first which provides a proposed system to evaluate the credibility of Twitter news content automatically.

This study aims to propose an unsupervised learning model to evaluate the credibility of disaster-related Twitter data and present a performance comparison with commonly used supervised machine learning models.

First historical tweets on two recent hurricane events are collected via Twitter API. Then a credibility scoring system is implemented in which the tweet features are analyzed to give a credibility score and credibility label to the tweet. After that, supervised machine learning classification is implemented using various classification algorithms and their performances are compared.

The proposed unsupervised learning model could enhance the emergency response by providing a fast way to determine the credibility of disaster-related tweets. Additionally, the comparison of the supervised classification models reveals that the Random Forest classifier performs significantly better than the SVM and Logistic Regression classifiers in classifying the credibility of disaster-related tweets.

In this paper, an unsupervised 10-point scoring model is proposed to evaluate the tweets’ credibility based on the user-based and content-based features. This technique could be used to evaluate the credibility of disaster-related tweets on future hurricanes and would have the potential to enhance emergency response during critical events. The comparative study of different supervised learning methods has revealed effective supervised learning methods for evaluating the credibility of Tweeter data.