Twitter Feed Research Articles

Automated Disaster Monitoring From Social Media Posts Using AI-Based Location Intelligence and Sentiment Analysis

Worldwide disasters like bushfires, earthquakes, floods, cyclones, and heatwaves have affected the lives of social media users in an unprecedented manner. They are constantly posting their level of negativity over the disaster situations at their location of interest. Understanding location-oriented sentiments about disaster situation is of prime importance for political leaders, and strategic decision-makers. To this end, we present a new fully automated algorithm based on artificial intelligence (AI) and natural language processing (NLP), for extraction of location-oriented public sentiments on global disaster situation. We designed the proposed system to obtain exhaustive knowledge and insights on social media feeds related to disaster in 110 languages through AI- and NLP-based sentiment analysis, named entity recognition (NER), anomaly detection, regression, and Getis Ord Gi* algorithms. We deployed and tested this algorithm on live Twitter feeds from 28 September to 6 October 2021. Tweets with 67 515 entities in 39 different languages were processed during this period. Our novel algorithm extracted 9727 location entities with greater than 70% confidence from live Twitter feed and displayed the locations of possible disasters with disaster intelligence. The rates of average precision, recall, and F₁-Score were measured to be 0.93, 0.88, and 0.90, respectively. Overall, the fully automated disaster monitoring solution demonstrated 97% accuracy. To the best of our knowledge, this study is the first to report location intelligence with NER, sentiment analysis, regression and anomaly detection on social media messages related to disasters and has covered the largest set of languages.

Tail Lights

1st October 2023. As autumn leaves fallsoftly and rustle to the ground, this poppedup on my Twitter feed: 52 years ago, the veryfirst CT scan was performed on a person.Godfrey Hounsfield was apparentlyintrigued by the notion of using cosmic raysto find hidden structures without “openingthe box” or entering ancient Egyptianpyramids. This brought to my mind thebeautiful bag Elliot (MedChir President,2022/23) gifted me on behalf of MedChir atthe Alumni Ball 2023. Why? Because the firstwoman featured on the bag is Cleopatra. Iloved it so much I ordered a few more forProfessor Judy Yee MD in New York City. Shewas chuffed and Twitter lit up with requestson where to buy them! (Supporting the localeconomy and all that….!)As we continue striving towards genderequality, I thought I’d share the wonderfulevent Elliot and the MedChir team pulledtogether for International Women’s Day,showcasing 4 amazing women Professors. Itwas a scintillating evening where we wereprivileged to hear and learn about their verydifferent careers and experiencesculminating in Professorships in Medicine.No mean feat by any standards! (Let meknow if you would like to attend anotherevening like this and I’ll see what we can do). Professor Rona Mackie / Lady Black another woman who changed the world!(disappointingly, not pictured on the bag) regrettably could not join us on the night. Asthe first woman appointed to an establishedChair at the University of Glasgow,Professor Mackie is a trailblazer, achievingand continuing to achieve so much in hercareer and life. As one of the foundingmembers of The Academy of MedicalSciences, not only has she been at theforefront of groundbreaking medicalresearch, but has also enabled others tocontinue advancing cutting edge medicine aswell as establishing one of the mostsuccessful medical mentoring programmes. Ihope you enjoy reading our little chat anddraw as much inspiration from it as I didmeeting her! Her vitality and formidability issomething that we should all aspire to!

Care workers in elder care: the Four Flows of constituting care organisations on social media

ABSTRACT This qualitative study delves into the impact of social media within a private elder care organisation, where its daily use was mandatory. It examines how care and care organizations take shape through the daily practices of care workers. Utilizing the concept of agency within the Communication Constituting Organisations framework (CCO) and its Four Flows model, we analyse how communication processes shape the organisational engagement of care workers. The study draws on interviews, observations, and a sample of the organisation's Twitter feed. The Four Flows illustrate care workers as proactive social media users motivated by personal values. While social media introduces new work tasks and alternative perspectives on traditional care, it also raises concerns about potentially prioritising technology over person-centric care. This research underscores how social media influences the content and methodologies of care within the framework of Communication Constituting Organisations (CCO) theories.

Congestion Detection with Sentiment Analysis

Abstract: This paper describes an approach to get insights into congestion on roads as well as get the general feedback of the state of transportation in a particular city and/or state. Google Maps gives you the location of the congestion but not the reason behind it. In this innovative approach, we try to extract the cause of the congestion as well as its severity with the help of sentiment analysis on Twitter feed. This data is especially helpful for authorities to arrange medical help, civic authorities for city planning as well as the common man who is new to a particular location.

Time Well Spent: Exploring the Role of Attitude and Topic Importance on Selective Exposure to Agricultural Messages

New digital technologies, such as Web 3.0 and algorithms, allow social media users to customize their feeds, creating their own information bubble, which tends to align with prior beliefs and/or attitude. This action of seeking information that emphasizes or confirms pre-existing beliefs is called confirmation bias, which is often expressed through selective exposure. Although previous studies have explored selective exposure in the context of political and health communications, limited research has been completed related to this phenomenon in agricultural communications. Therefore, the purpose of this study was to explore the effects of attitude and topic importance on selective exposure to different agricultural messages. Using a quasi-experimental design, this study used a Qualtrics questionnaire to collect data from undergraduate students in a laboratory setting. Participants provided their attitudes and topic important for two agricultural issues. A fictional Twitter feed was created that linked to four blog posts that served as the message stimuli. To determine selective exposure, we recorded how many blog posts they selected and how long they spent on each message. The results indicated that participants had varying attitudes of the two agricultural topics but had equal views of importance. No significant difference in time spent on the messages on was found. The results indicated that the process of selective exposure is a complex construct that involves many factors. Additional research in this area will help agricultural communicators develop more effective message strategies and understand the role of confirmation bias in information processing.

Dalit Histories, Pandemic Histories

Dalit Histories, Pandemic Histories

Leading brand communication during crises: COVID-19 lockdown at Gautrain, South Africa

Learning outcomes The learning outcomes of this study are as follows: 1. comprehending foundational dimensions of brand equity and criteria to compare the use of traditional and new media in leading brand communication appropriateness and performance; 2. understanding and evaluating implications of leading brand communications during times of crises; and 3. creating recommendations for leading brand communication preparedness and response to crises. Case overview/synopsis On 16 August 2020, Dr Barbara Jensen Vorster, Senior Executive Manager, Communications and Marketing of the Gautrain Management Agency (GMA), in Midrand South Africa, considered her dilemma of adapting their communication approach during COVID-19 and beyond the current crisis. The GMA relied on traditional media and the crisis created an opportunity to rethink their entire communications approach. It was important to the GMA communications team to keep the Gautrain commuters connected even though they might not be using the Gautrain during the lockdown of COVID-19. Jensen Vorster believed that a brand should be adaptive and continue even when a service is not running. Jensen Vorster had to lead her communications team when they were all working from home, and they had to keep commuters informed of the requirements during the different levels of lockdown in South Africa. Their various campaigns during this time purposefully communicated with commuters and the various “staying home” initiatives with the intention of lifting spirits. The communication outreach during the COVID-19 pandemic switched over to social media communications out of necessity; however, was that ideal communication during a crisis? While most of the case focuses on this external communication, the case pays attention to some internal communication initiatives by Jensen Vorster with her own team and for the Gautrain’s staff. The question is whether brands should shift from traditional media to new media campaigns during the 21st-century crises? Students will get the opportunity to compare the use of traditional and new media during crisis times. How might they approach their brand communications during COVID-19 and in preparation for future crises? Complexity academic level Marketing and Business Communications and Leadership courses for MBA or executive education programs. Study level/applicability Masters level MBA. Research method The team of authors conducted face-to-face interviews prior to and during the lockdown in South Africa; the interviews were conducted online through Zoom. Interviews included Dr Barbara Jensen Vorster, Senior Executive Manager, Communications and Marketing of the Gautrain Management Agency and Kesagee Nayager, the Marketing and Communications Executive Manager at Bombela Concession Company. Viwe Mgedzi, Executive Manager for Knowledge Management, provided documents supporting the case. The researchers also conducted desktop research of secondary data, including media and press articles on the companies. The @Gautrain Twitter feed was very important for the researchers to investigate as part of the secondary data research, to triangulate the interview data. For example, see one of the Twitter feeds on 17 March 2020, 5:37 pm. The following Twitter feed on the Gautrain’s status confirmed the interview data: https://twitter.com/TheGautrain/status/1239938937885466633 The main resources of this case study were the interviews and the media articles to offer objective references. The authors used the following two newspaper articles to triangulate the information they gained from the interviews: BusinessTech, March 18, 2020, accessed March 8, 2021 at https://businesstech.co.za/news/lifestyle/382707/south-african-coronavirus-cases-jumps-to-116-as-a-gautrain-exec-tests-positive/ Timeslive, www.timeslive.co.za/news/south-africa/2020-03-17-staff-in-self-isolation-after-executive-tests-positive-two-gautrain-stations-chemically-decontaminated/ Supplementary materials Teaching notes are available for educators only. Subject code CSS 7: Management science; CSS 8: Marketing.

Close, but No Cigar

Close, but No Cigar

Scrutinising medical practitioners' Twitter feeds: an analysis

Mining of social media data has found widespread applications in recent times. Twitter feeds and Facebook posts are being used to device product marketing strategies, sentiment analysis, financial predictions and forebode alarming situations. Twitter feeds analysis can be applied for analysing the behaviour and experiences of medical practitioners. Doctors' informal conversations on Twitter can provide deep insights about their work experiences, their concerns about the profession, their feelings - pathos or excitement they feel - and the affecting conditions. In the present work, Twitter feed of doctors along with the Twitter hashtags are used to collect data from tweets with hashtags such as #DoctorProblems. Afterward, data analysis was performed to determine the major problems faced by the members of the medical fraternity. These problems were categorised into five main categories. The multi-label na

A decision support system for extracting artificial intelligence-driven insights from live twitter feeds on natural disasters

Existing studies on Twitter-based natural disaster analysis suffer from shortcomings like limitations on supported languages, lack of sentiment analysis, regional restrictions, lack of end-to-end automation, and lack of Mobile App support. In this study, we design and develop a fully-automated artificial intelligence (AI) based Decision Support System (DSS) available through multiple platforms like iOS, Android, and Windows. The proposed DSS uses a live Twitter feed to obtain natural disaster-related Tweets in 110 supported languages. The system automatically executes AI-based translation, sentiment analysis, and automated K-Means algorithm to generate AI-driven insights for disaster strategists. The proposed DSS was tested with 67,528 real-time Tweets captured between 28 September 2021 and 6 October 2021 in 39 different languages under two different scenarios. The system revealed critical information for disaster planners or strategists like which clusters of natural disasters were associated with the most negative sentiments. We evaluated the proposed system’s accuracy and user experiences from 12 different disaster strategists. 83.33% of users found the proposed solution easy to use, effective, and self-explanatory. With 97% and 99.7% accuracy in Twitter keyword extraction and entity classification, this DSS reported the most accurate disaster intelligence system on a mobile platform.

People and nature: The emerging signature of a relational journal

People and nature: The emerging signature of a relational journal

Detecting damaged buildings using real-time crowdsourced images and transfer learning

After significant earthquakes, we can see images posted on social media platforms by individuals and media agencies owing to the mass usage of smartphones these days. These images can be utilized to provide information about the shaking damage in the earthquake region both to the public and research community, and potentially to guide rescue work. This paper presents an automated way to extract the damaged buildings images after earthquakes from social media platforms such as Twitter and thus identify the particular user posts containing such images. Using transfer learning and ~ 6500 manually labelled images, we trained a deep learning model to recognize images with damaged buildings in the scene. The trained model achieved good performance when tested on newly acquired images of earthquakes at different locations and when ran in near real-time on Twitter feed after the 2020 M7.0 earthquake in Turkey. Furthermore, to better understand how the model makes decisions, we also implemented the Grad-CAM method to visualize the important regions on the images that facilitate the decision.

David Liew: where communication meets medicine

“The honest truth is that I find it difficult to talk about myself. I’m really quite self-conscious.” It wasn’t what I expected to hear from David Liew, guest host of The Lancet Rheumatology's Clinical Realities podcast. Having hosted a plethora of other podcasts for RheumNow and other outlets, I thought he might be an extrovert. I wonder if he is perhaps the shy actor type who has no problem playing to the camera but who clams up when one-on-one. But when he starts talking about what he does, the easy-going person I expected begins to appear. Many people will know David from his internet presence, including his many videos, his conference reporting, his feature-type articles, and a Twitter feed that pumps out rheumatology news, but he is also consultant rheumatologist, clinical pharmacologist, and project lead of the Medicines Optimisation Service at the Austin Hospital (Heidelberg, VIC, Australia), although too modest to actually tell me much about these roles.

Leveraging Twitter and its Unique #HashTag Capability: A Novel Social Media Resource From the European Hernia Society.

Background: Digital and Social Media (#SoMe) platforms have revolutionized the way information is shared, classified and accessed among medical professionals worldwide. The aim of this study was to review the hashtags used on Twitter by @EuroHerniaS to provide a practical roadmap for easier social media utilization for hernia surgery stakeholders. Methods: The hashtags used in tweets and retweets of the @EuroHerniaS Twitter feed were collated since its foundation in November 2016. Results: The first hashtag used was #HerniaSurgery. Since foundation to July 2021, the @EuroHerniaS Twitter feed has used 90 separate hashtags. The number of new hashtags per year was increasing leading to the development of an online library. The increasing diversity of hernia related hashtags allows for the more detailed posting and searching of hernia related information on the #SoMe platform Twitter. Conclusion: The more detailed use of hashtags on Twitter is to be encouraged. Hernia surgeons can make use of them both when posting and reviewing posts to aid the categorization of posts.

What do riders say and where? The detection and analysis of eyewitness transit tweets

Information shared on social media by transit system customers is often candid, localized, and includes in the moment information about emerging events or issues. Twitter provides an unfiltered and timestamped feed of information that can be aggregated to generate valuable insights. Our research aims to identify passenger-related transit incidents from a public Twitter feed. Detecting these incidents in real time enables transit agencies to immediately respond to them by dispatching security, safety, or maintenance crews or by rapidly replying to requests made to the agency that are urgent in nature. We leverage natural language processing to extract latent information from identified eyewitness tweets about transit, focusing on location details, topic classification, and sentiment analysis. We outline an approach to developing a useful corpus of transit-focused tweets, detecting in the moment events, classifying these tweets into topics, and detecting locations where possible. We then demonstrate the approach through an application to Calgary Transit in Calgary, Canada. The results demonstrate that key incidents can be identified and prioritized for an agency.

AI-based Automated Extraction of Location-Oriented COVID-19 Sentiments

The coronavirus disease (COVID-19) pandemic has affected the lives of social media users in an unprecedented manner. They are constantly posting their satisfaction or dissatisfaction over the COVID-19 situation at their location of interest. Therefore, understanding location-oriented sentiments about this situation is of prime importance for political leaders, and strategic decision-makers. To this end, we present a new fully automated algorithm based on artificial intelligence (AI), for extraction of location-oriented public sentiments on the COVID-19 situation. We designed the proposed system to obtain exhaustive knowledge and insights on social media feeds related to COVID-19 in 110 languages through AI-based translation, sentiment analysis, location entity detection, and decomposition tree analysis. We deployed fully automated algorithm on live Twitter feed from July 15, 2021 and it is still running as of 12 January, 2022. The system was evaluated on a limited dataset between July 15, 2021 to August 10, 2021. During this evaluation timeframe 150,000 tweets were analyzed and our algorithm found that 9,900 tweets contained one or more location entities. In total, 13,220 location entities were detected during the evaluation period, and the rates of average precision and recall rate were 0.901 and 0.967, respectively. As of 12 January, 2022, the proposed solution has detected 43,169 locations using entity recognition. According to the best of our knowledge, this study is the first to report location intelligence with entity detection, sentiment analysis, and decomposition tree analysis on social media messages related to COVID-19 and has covered the largest set of languages.

To TikTok or not?

TikTok is wildly popular. Even if you're not active on the app itself, you've likely seen a TikTok video shared in your Facebook or Twitter feed — or as a clip featured on your favorite late‐night TV show.

A Conversation With … Kamali Thompson MD, MBA, US Olympic Alternate in Fencing and Orthopaedic Surgery Resident.

A Conversation With … Kamali Thompson MD, MBA, US Olympic Alternate in Fencing and Orthopaedic Surgery Resident.

Major League Missteps: How MLB Mishandled the Astros Cheating Scandal

Major League Baseball (MLB) has been criticized for its handling of the Astros’ cheating scandal. Researchers used a case study method to test whether Situational Crisis Communication Theory (SCCT) should be expanded to include collaborative brand attack (CBA) as a crisis type. Researchers used traditional and extended SCCT to analyze MLB’s crisis response to determine which version fit best. Data were triangulated from sports news sources, MLB’s official statement and Twitter account, and social media influencer and stakeholder posts. Researchers asked which SCCT response MLB used and whether it was effective with stakeholders. Because of poor history, MLB’s accidental crisis response mismatched the level of stakeholder attribution of responsibility. Another question examined the role of social media. Major League Baseball underestimated the role of social media and SM influencers and, by underutilizing its Twitter feed, left stakeholders to attribute greater responsibility to MLB. Two final questions asked whether SCCT should be updated to include the CBA crisis type and whether it applied in this case. The results indicate the negative consequences of crisis/response mismatch and indicate that CBA should be incorporated into SCCT to address social media influence. This is the first known study to apply CBA in a sports context.

To TikTok or not?

TikTok is wildly popular. Even if you're not active on the app itself, you've likely seen a TikTok video shared in your Facebook or Twitter feed — or as a clip featured on your favorite late‐night TV show.