scholarly journals SMAFED: Real-Time Event Detection in Social Media Streams

2021 ◽  
Author(s):  
Taiwo Kolajo ◽  
Olawande Daramola ◽  
Ayodele A. Adebiyi
Keyword(s):  
Social Media ◽  
Event Detection ◽  
Semantic Processing ◽  
Semantic Analysis ◽  
Semantic Representation ◽  
Semantic Relatedness ◽  
Media Analysis ◽  
Social Media Platforms ◽  
Media Stream ◽  
The Impact

Abstract Interactions via social media platforms have made it possible for anyone, irrespective of physical location, to gain access to quick information on events taking place all over the globe. However, the semantic processing of social media data is complicated due to challenges such as language complexity, unstructured data, and ambiguity. In this paper, we proposed the Social Media Analysis Framework for Event Detection (SMAFED). SMAFED aims to facilitate improved semantic analysis of noisy terms in social media streams, improved representation/embedding of social media stream content, and improved summarisation of event clusters in social media streams. For this, we employed key concepts such as integrated knowledge base, resolving ambiguity, semantic representation of social media streams, and Semantic Histogram-based Incremental Clustering based on semantic relatedness. Two evaluation experiments were conducted to validate the approach. First, we evaluated the impact of the data enrichment layer of SMAFED. We found that SMAFED outperformed other pre-processing frameworks with a lower loss function of 0.15 on the first dataset and 0.05 on the second dataset. Secondly, we determined the accuracy of SMAFED at detecting events from social media streams. The result of this second experiment showed that SMAFED outperformed existing event detection approaches with better Precision (0.922), Recall (0.793), and F-Measure (0.853) metric scores. The findings of the study present SMAFED as a more efficient approach to event detection in social media.

scholarly journals Stayhome Hashtag: Sentiment Analysis on Twitter During the Covid-19 Pandemic

2020 ◽  
Vol 16 (34) ◽  
Author(s):  
Ugur Gunduz
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
Disaster Management ◽  
Semantic Analysis ◽  
Global Epidemic ◽  
Social Media Platforms ◽  
The Difference ◽  
Textual Content ◽  
The Impact ◽  
Media Data

With developing technology today, social media has entered every area of our lives. Many people come together and share in social media platforms without time and space restrictions. Social media has been in our lives so much lately. It is an undeniable fact that global outbreaks, which constitute an important part of our lives, are also affected by these networks and that they exist in these networks and share the users. The purpose of making this hashtag analysis is to reveal the difference in discourse and language while analyzing twitter data, while doing this, to evaluate the effects of a global epidemic crisis on language, message and crisis management with social media data. Sentiment analysis of tweets, on the other hand, objectives to take a look at the contents of these messages, to degree the feelings and feelings conveyed. This form of analysis is typically completed through amassing textual content data, then investigating the “sentiment” conveyed. Within the scope of our study, one hundred thousand twitter messages posted with the #stayhome hashtag between 23 May 2020 and 29 May 2020 were examined. The impact and reliability of social media in disaster management could be questioned by carrying out a content analysis based totally on the semantic analysis of the messages given on the Twitter posts with the phrases and frequencies used. Social media and Twitter content are increasingly more identified as treasured resources of public health signals concerning use in ailment surveillance and health disaster management.

scholarly journals A Tale of Two Disasters

2020 ◽  
Vol 4 (Supplement_1) ◽  
pp. 694-694
Author(s):  
Tammy Mermelstein
Keyword(s):  
Older Adults ◽  
Social Media ◽  
Interest Group ◽  
Media Analysis ◽  
Ice Storm ◽  
Social Media Analysis ◽  
Individual Survival ◽  
Social Media Platforms

Abstract Preparing for or experiencing a disaster is never easy, but how leaders communicate with older adults can ease a situation or make it exponentially worse. This case study describes two disasters in the same city: Hurricane Harvey and the 2018 Houston Texas Ice Storm and the variation in messaging provided to and regarding older adults. For example, during Hurricane Harvey, the primary pre-disaster message was self-preparedness. During the storm, messages were also about individual survival. Statements such as “do not [climb into your attic] unless you have an ax or means to break through,” generated additional fear for older adults and loved ones. Yet, when an ice storm paralyzed Houston a few months later, public messaging had a strong “check on your elderly neighbors” component. This talk will explore how messaging for these events impacted older adults through traditional and social media analysis, and describe how social media platforms assisted people with rescue and recovery. Part of a symposium sponsored by Disasters and Older Adults Interest Group.

scholarly journals Embed2Detect: temporally clustered embedded words for event detection in social media

2021 ◽  
Author(s):  
Hansi Hettiarachchi ◽  
Mariam Adedoyin-Olowe ◽  
Jagdev Bhogal ◽  
Mohamed Medhat Gaber
Keyword(s):  
Social Media ◽  
Event Detection ◽  
High Volume ◽  
Detection Methods ◽  
Word Embeddings ◽  
Agglomerative Clustering ◽  
Data Set ◽  
Social Media Data ◽  
Social Media Platforms ◽  
Media Data

AbstractSocial media is becoming a primary medium to discuss what is happening around the world. Therefore, the data generated by social media platforms contain rich information which describes the ongoing events. Further, the timeliness associated with these data is capable of facilitating immediate insights. However, considering the dynamic nature and high volume of data production in social media data streams, it is impractical to filter the events manually and therefore, automated event detection mechanisms are invaluable to the community. Apart from a few notable exceptions, most previous research on automated event detection have focused only on statistical and syntactical features in data and lacked the involvement of underlying semantics which are important for effective information retrieval from text since they represent the connections between words and their meanings. In this paper, we propose a novel method termed Embed2Detect for event detection in social media by combining the characteristics in word embeddings and hierarchical agglomerative clustering. The adoption of word embeddings gives Embed2Detect the capability to incorporate powerful semantical features into event detection and overcome a major limitation inherent in previous approaches. We experimented our method on two recent real social media data sets which represent the sports and political domain and also compared the results to several state-of-the-art methods. The obtained results show that Embed2Detect is capable of effective and efficient event detection and it outperforms the recent event detection methods. For the sports data set, Embed2Detect achieved 27% higher F-measure than the best-performed baseline and for the political data set, it was an increase of 29%.

scholarly journals 1414. #Vaccine Twitter Influencers: is it Just About Reach and Followers?

2020 ◽  
Vol 7 (Supplement_1) ◽  
pp. S714-S715
Author(s):  
Jean-Etienne Poirrier ◽  
Theodore Caputi ◽  
John Ayers ◽  
Mark Dredze ◽  
Sara Poston ◽  
...  
Keyword(s):  
United States ◽  
Social Media ◽  
Standard Deviation ◽  
Small Proportion ◽  
The United States ◽  
Research Support ◽  
Policy Makers ◽  
Media Messages ◽  
Social Media Platforms ◽  
The Impact

Abstract Background A small number of powerful users (“influencers”) dominates conversations on social media platforms: less than 1% of Twitter accounts have at least 3,000 followers and even fewer have hundreds of thousands or millions of followers. Beyond simple metrics (number of tweets, retweets...) little is known about these “influencers”, particularly in relation to their role in shaping online narratives about vaccines. Our goal was to describe influential Twitter accounts that are driving conversations about vaccines and present new metrics of influence. Methods Using publicly-available data from Twitter, we selected posts from 1-Jan-2016 to 31-Dec-2018 and extracted the top 5% of accounts tweeting about vaccines with the most followers. Using automated classifiers, we determined the location of these accounts, and grouped them into those that primarily tweet pro- versus anti-vaccine content. We further characterized the demographics of these influencer accounts. Results From 25,381 vaccine-related tweets available in our sample representing 10,607 users, 530 accounts represented the top 5% by number of followers. These accounts had on average 1,608,637 followers (standard deviation=5,063,421) and 340,390 median followers. Among the accounts for which sentiment was successfully estimated by the classifier, 10.4% (n=55) posted anti-vaccine content and 33.6% (n=178) posted pro-vaccine content. Of the 55 anti-vaccine accounts, 50% (n=18) of the accounts for which location was successfully determined were from the United States. Of the 178 pro-vaccine accounts, 42.5% (n=54) were from the United States. Conclusion This study showed that only a small proportion of Twitter accounts (A) post about vaccines and (B) have a high follower count and post anti-vaccine content. Further analysis of these users may help researchers and policy makers better understand how to amplify the impact of pro-vaccine social media messages. Disclosures Jean-Etienne Poirrier, PhD, MBA, The GSK group of companies (Employee, Shareholder) Theodore Caputi, PhD, Good Analytics Inc. (Consultant) John Ayers, PhD, GSK (Grant/Research Support) Mark Dredze, PhD, Bloomberg LP (Consultant)Good Analytics (Consultant) Sara Poston, PharmD, The GlaxoSmithKline group of companies (Employee, Shareholder) Cosmina Hogea, PhD, GlaxoSmithKline (Employee, Shareholder)

Understanding the Experiences of Anger in the Onset and Progression of Psoriasis: A Qualitative Study Using Social Media (Preprint)

2021 ◽  
Author(s):  
Olivia Hughes ◽  
Rachael Hunter
Keyword(s):  
Social Media ◽  
Qualitative Interviews ◽  
Psychosocial Interventions ◽  
Skin Condition ◽  
Future Research ◽  
Social Media Platforms ◽  
Chronic Skin ◽  
Skin Conditions ◽  
The Impact

BACKGROUND Psoriasis is a chronic inflammatory skin condition, which can be affected by stress. Living with psoriasis can trigger negative emotions, which may influence quality of life. OBJECTIVE This study explored the experiences of people with psoriasis with attention to the potential role of anger in the onset and progression of the chronic skin condition. METHODS Semi-structured qualitative interviews were conducted with twelve participants (n=5 females, n=7 males) recruited online from an advert on a patient charity’s social media platforms. Data were transcribed and analysed using thematic analysis. RESULTS Four key themes were identified: (1) ‘I get really angry with the whole situation:’ anger at the self and others, (2) the impact of anger on psoriasis: angry skin, (3) shared experiences of distress, and (4) moving past anger to affirmation. CONCLUSIONS Findings suggest that anger can have a perceived impact on psoriasis through contributing to sensory symptoms and unhelpful coping cycles and point to a need for enhanced treatment with more psychological support. The findings also highlight the continued stigma which exists for people living with skin conditions and how this may contribute to, and sustain, anger for those individuals. Future research could usefully focus on developing targeted psychosocial interventions to promote healthy emotional coping with psoriasis.

scholarly journals Quantifying and contextualizing the impact of bioRxiv preprints through automated social media audience segmentation

2020 ◽  
Author(s):  
Jedidiah Carlson ◽  
Kelley Harris
Keyword(s):  
Social Media ◽  
Video Game ◽  
Research Evaluation ◽  
Right Wing ◽  
Religious Groups ◽  
Audience Segmentation ◽  
Social Media Platforms ◽  
Game Developers ◽  
The Impact ◽  
Media Audience

AbstractEngagement with scientific manuscripts is frequently facilitated by Twitter and other social media platforms. As such, the demographics of a paper’s social media audience provide a wealth of information about how scholarly research is transmitted, consumed, and interpreted by online communities. By paying attention to public perceptions of their publications, scientists can learn whether their research is stimulating positive scholarly and public thought. They can also become aware of potentially negative patterns of interest from groups that misinterpret their work in harmful ways, either willfully or unintentionally, and devise strategies for altering their messaging to mitigate these impacts. In this study, we collected 331,696 Twitter posts referencing 1,800 highly tweeted bioRxiv preprints and leveraged topic modeling to infer the characteristics of various communities engaging with each preprint on Twitter. We agnostically learned the characteristics of these audience sectors from keywords each user’s followers provide in their Twitter biographies. We estimate that 96% of the preprints analyzed are dominated by academic audiences on Twitter, suggesting that social media attention does not always correspond to greater public exposure. We further demonstrate how our audience segmentation method can quantify the level of interest from non-specialist audience sectors such as mental health advocates, dog lovers, video game developers, vegans, bitcoin investors, conspiracy theorists, journalists, religious groups, and political constituencies. Surprisingly, we also found that 10% of the highly tweeted preprints analyzed have sizable (>5%) audience sectors that are associated with right-wing white nationalist communities. Although none of these preprints intentionally espouse any right-wing extremist messages, cases exist where extremist appropriation comprises more than 50% of the tweets referencing a given preprint. These results present unique opportunities for improving and contextualizing research evaluation as well as shedding light on the unavoidable challenges of scientific discourse afforded by social media.

scholarly journals Impact of the COVID-19 Pandemic on Instagram and Influencer Marketing

2021 ◽  
Vol 13 (2) ◽  
pp. 20
Author(s):  
Evelina Francisco ◽  
Nadira Fardos ◽  
Aakash Bhatt ◽  
Gulhan Bizel
Keyword(s):  
Social Media ◽  
Marketing Strategy ◽  
Online Survey ◽  
Video Conferencing ◽  
Marketing Mix ◽  
The Internet ◽  
Exploratory Research ◽  
Social Media Platforms ◽  
The Impact ◽  
Made In

The COVID-19 pandemic and the resulting stay-at-home orders have disrupted all aspects of life globally, most notably our relationship with the internet and social media platforms. People are online more than ever before, working and attending school from home and socializing with friends and family via video conferencing. Marketers and brands have been forced to adapt to a new normal and, as a result, have shifted their brand communication and marketing mix to digital approaches. Hence, this study aims to examine the shift of influencer marketing on Instagram during this period and the possible future implications. By employing an online survey for exploratory research, individuals answered questions addressing their perceptions about the impact of the pandemic, brands and influencers’ relationship, and the overall changes made in marketing strategy.

scholarly journals A Pilot Study on the Impact of Facebook on Perceptions of Police Force

2019 ◽  
Vol 3 (1) ◽  
pp. 6-11
Author(s):  
Wayne W. L. Chan ◽  
Keyword(s):  
Social Media ◽  
Social Networking ◽  
Public Perception ◽  
Public Discourse ◽  
Police Force ◽  
Online Social Networking ◽  
Individual Interviews ◽  
Social Media Platforms ◽  
Perceptions Of Police ◽  
The Impact

The legal authorities, particularly the police force, have been increasingly facing challenges given the popularity of social media [1, 2]. However, we know very little about how public perceptions of the police are being shaped by social media. In this context, this study attempted to investigate the impact of social media on young people’s perceptions of the police in Hong Kong. The focus of this study was placed on Facebook since it was one of the most popular social media platforms in the city. Facebook was not only conceptualized as a communication medium but also a social networking arena. In this connection, qualitative individual interviews were conducted to explore the online social networking on Facebook and its relation to the perceptions of police force. It was found that the Facebook users who were more likely to stay closely connected with other users with similar views would tend to form the politicized perception of police force. On the other hand, the Facebook users who were to be networked with some other users or real persons with dissimilar views would hold more neutral perceptions of the police. This study was the first of its kind to investigate the role of online social networking in the perceptions of the police, thus filling an important gap in our knowledge of the increasing impact of social media. Therefore, the results of current study were expected to contribute to society by avoiding the disproportionate public discourse about law and order. Keywords: Social Media, Online Social Networking, Public Perception, Police Force.

scholarly journals Sensing And Detecting Small-Scale Events Using Geosocial Media Data

2021 ◽  
Author(s):  
Shishuo Xu
Keyword(s):  
Social Media ◽  
Event Detection ◽  
Human Movement ◽  
Small Scale ◽  
Type I ◽  
Social Event ◽  
Ground Truth Data ◽  
Social Events ◽  
Social Media Platforms ◽  
Media Data

<div>Small-scale events involve interactive human movement in limited space and time. Social media platforms possibly generate large amount of geospatially-referenced information related to small-scale events. It benefits individuals, management departments, and urban systems if small-scale events can be timely detected from social media platforms, where measuring the abnormal patterns of human movement to discover events and analyzing associated texts to interpret the reasons behind abnormal movement are two keys. Through investigating how people move as different events occur and measuring the patterns on social media platforms, small-scale events can be generally classified into two types, namely type I events with abrupt patterns and type II events with random occurrence of key factors, where social events and traffic events are representative correspondingly.</div><div>Despite many studies have been conducted to detect social events and traffic events using geosocial media data, there still are some un-answered questions requiring further research. Most existing studies did not identify occurring events from a full coverage of spatial, temporal, and semantic perspectives. Studies concerning social event detection lack efficient semantic analysis summarizing event content to infer the reasons driving the abnormal movement. The typical classification-based method regarding traffic event detection lacks investigation on how the spatiotemporal distribution of traffic relevant posts associate with the occurring traffic events, and simply assigns the detected events with predefined categories, missing events that indicate traffic anomalies but go beyond the predetermined categories.<br></div><div>In this thesis, spatial-temporal-semantic approaches are proposed to measure spatiotemporal patterns of posts and users of social media platforms to capture abnormal human movement, and analyze the content of associated posts to mine the reasons driving the movement. A variety of techniques including machine learning, natural language processing, and spatiotemporal analysis are adopted to realize effective detection. Based on one-year Twitter data collected in Toronto, 2014 Toronto International Film Festival and traffic anomaly detection are selected as two case studies to evaluate the performance of proposed approaches. Through comparing with the ground truth data, the result reveals that more than 80% of the detected events do refer to real-world events, which illustrates the feasibility and efficiency of proposed approaches.<br></div><div><br></div><div>Keywords: Small-scale event, Event detection, Geosocial media data, Traffic event, Social event, Twitter, Spatiotemporal clustering<br></div>

Sign in / Sign up

Export Citation Format

Share Document