Content Of Tweets Research Articles

Modeling the debate dynamics of political communication in social media networks

Social networks' ability to disseminate content to millions of users with just one click has made them a major playground for political marketing. Campaigners seek to identify a small subset of seed users in a social network to maximize the spread of influence. However, political content diffusion has a distinct nature —some users may invert a message's content before sending it onward, thereby propagating a view that contradicts the one held by the original author. Here, we developed a novel transmission model tailored to analyze the effect of debate dynamics in realistic settings of social networks. We demonstrate our model on a real-world network we developed based on a large-scale dataset of 715K tweets discussing active political content concerning the Israeli-Palestinian conflict. Our simulations reveal that even a minute probability of tweet content inversion could result in the message being echoed, spread, and amplified by opposing users. The profile of the optimal seed users who would maximize exposure, too, drastically changes, and “echo chambers” are intensified compared to a no-inversion setting. Neglecting the effect of inversion may even result in a counterproductive outcome from the perspective of the original authors. Campaigners can significantly benefit from explicitly accounting for the impact of content inversion in social networks.

#SurgOnc: Global discussions about surgical cancer care on Twitter during COVID-19.

11045 Background: Social media platforms such as Twitter are highly utilized to communicate about cancer care. Although surgery is the primary treatment for solid malignancies, little is known about public perceptions or communication behaviors regarding this treatment modality. Further, prolonged lockdowns and widespread delays of planned operations during the COVID-19 pandemic have magnified the importance of virtual communication about surgical cancer care. Methods: Tweets referencing cancer surgery were collected from January 2018 to January 2022 using Twitter’s Application Programming Interface. Account metadata was used to predict user demographic information and to compare tweeting metrics across users. Natural language processing models were applied to tweet content to resolve common topics of conversation and to classify tweets by cancer type. Results: There were 442,840 original tweets about cancer surgery by 262,168 users. Individuals accounted for most users (65%) while influencers accounted for the least (1.4%). Influencers made the most median impressions (19,139). Of 240,713 tweets discussing surgery for specific cancers, breast (20%) and neurologic (17%) cancers were most mentioned. When adjusting for national rates of procedures performed, tweets about surgery for neurologic cancers were the most common (231 tweets per 1000 procedures) whereas those for urologic cancers were the least common (15 tweets per 1000 procedures). Discussions about cancer surgery research made up 31% of tweets before the pandemic but only 11% of tweets during the pandemic. During the pandemic, concern regarding COVID-19 related delays was the most tweeted topic (23%). Cancer surgery research was most cited by oncologists, as well as in tweets about hepatopancreatobiliary and colorectal cancers. The cost of surgery was commonly mentioned in tweets about breast and gynecologic cancers and contained the most negative sentiment score (-0.7). Conclusions: Twitter was highly utilized to discuss surgical cancer care during the COVID-19 pandemic. During the pandemic, conversations shifted focus from research to survivorship and reflected real-time events such as COVID-19-related surgical delays. We identified the financial burden of cancer care as a commonly held concern among patients discussing cancer surgery on social media. Future public health outreach about cancer surgery may be optimized by coordinating with influencers and by targeting topics of concern like cost of surgery and undermentioned content like urologic cancers. Twitter’s role as a platform for research dissemination was disrupted by the COVID-19 pandemic, and further tracking is needed regarding online research discussions after the pandemic.

Fake accounts detection system based on bidirectional gated recurrent unit neural network

<span>Online social networks have become the most widely used medium to interact with friends and family, share news and important events or publish daily activities. However, this growing popularity has made social networks a target for suspicious exploitation such as the spreading of misleading or malicious information, making them less reliable and less trustworthy. In this paper, a fake account detection system based on the bidirectional gated recurrent unit (BiGRU) model is proposed. The focus has been on the content of users’ tweets to classify twitter user profile as legitimate or fake. Tweets are gathered in a single file and are transformed into a vector space using the GloVe word embedding technique in order to preserve the semantic and syntax context. Compared with the baseline models such as long short-term memory (LSTM) and convolutional neural networks (CNN), the results are promising and confirm that using GloVe with BiGRU classifier outperforms with 99.44% for accuracy and 99.25% for precision. To prove the efficiency of our approach the results obtained with GloVe were compared to Word2vec under the same conditions. Results confirm that GloVe with BiGRU classifier performs the best results for detection of fake Twitter accounts using only tweets content feature.</span>

A Digital Diplomacy Irony: Donald Trump

The concept of digital diplomacy includes the use of digital communication techniques both in interstate diplomacy and in the relationship between a state and foreign public opinion groups. This study is a qualitative research to determine how the 45th President of the USA, Donald John Trump, uses Twitter in terms of content in the context of digital diplomacy. The general purpose of the study is to evaluate Trump's digital diplomacy activities on Twitter. In this context, examining the styles and forms of the role of digital diplomacy constitutes the main research question of this study. The question of how Trump's digital diplomacy practices on Twitter are, constitutes the main problematic to focus on in the research. In the study, firstly, the literature on the subject was searched, and then Trump's tweets containing diplomacy issues between January 20, 2017 and January 20, 2021 were taken as a basis in the selection of the data needed for the research. In the process of collecting data within the scope of the research, document analysis method was used. In the content analysis carried out on the determined sample, categories were produced based on the diplomacy actors that are frequently repeated in the literature, and each analyzed tweet was analyzed within the relevant category. One of the most basic findings obtained as a result of the research is the fact that the language he uses while using social media is quite far from the language of diplomacy due to Trump's tweets. In addition, it is noteworthy that Trump exhibits a racist attitude and uses hate language with tweets he sends to both himself and other countries' citizens and administrations on Twitter, one of his social media channels. Looking at the data, it is seen that soft power elements are not used in the content of Trump's tweets, therefore, there is no national and international dialogue environment, and it is concluded that his tweets have reached the level of sarcastic, insulting and even hate crime, and therefore it can be called digital diplomacy irony.

Sentiment Analysis of COVID-19 Tweets Using Adaptive Neuro-Fuzzy Inference System Models

In today’s digital era, Twitter’s data has been the focus point among researchers as it provides specific data and in a wide variety of fields. Furthermore, Twitter’s daily usage has surged throughout the coronavirus disease (Covid-19) period, presenting a unique opportunity to analyze the content and sentiment of covid-19 tweets. In this paper, a new approach is proposed for the automatic sentiment classification of Covid-19 tweets using the Adaptive Neuro-Fuzzy Inference System (ANFIS) models. The entire process includes data collection, pre-processing, word embedding, sentiment analysis, and classification. Many experiments were accomplished to prove the validity and efficiency of the approach using datasets Covid-19 tweets and it accomplished the data reduction process to achieve considerable size reduction with the preservation of significant dataset's attributes. Our experimental results indicate that fuzzy deep learning achieves the best accuracy (i.e. 0.916) with word embeddings.

An Analysis of French-Language Tweets About COVID-19 Vaccines: Supervised Learning Approach.

BackgroundAs the COVID-19 pandemic progressed, disinformation, fake news, and conspiracy theories spread through many parts of society. However, the disinformation spreading through social media is, according to the literature, one of the causes of increased COVID-19 vaccine hesitancy. In this context, the analysis of social media posts is particularly important, but the large amount of data exchanged on social media platforms requires specific methods. This is why machine learning and natural language processing models are increasingly applied to social media data.ObjectiveThe aim of this study is to examine the capability of the CamemBERT French-language model to faithfully predict the elaborated categories, with the knowledge that tweets about vaccination are often ambiguous, sarcastic, or irrelevant to the studied topic.MethodsA total of 901,908 unique French-language tweets related to vaccination published between July 12, 2021, and August 11, 2021, were extracted using Twitter’s application programming interface (version 2; Twitter Inc). Approximately 2000 randomly selected tweets were labeled with 2 types of categorizations: (1) arguments for (pros) or against (cons) vaccination (health measures included) and (2) type of content (scientific, political, social, or vaccination status). The CamemBERT model was fine-tuned and tested for the classification of French-language tweets. The model’s performance was assessed by computing the F1-score, and confusion matrices were obtained.ResultsThe accuracy of the applied machine learning reached up to 70.6% for the first classification (pro and con tweets) and up to 90% for the second classification (scientific and political tweets). Furthermore, a tweet was 1.86 times more likely to be incorrectly classified by the model if it contained fewer than 170 characters (odds ratio 1.86; 95% CI 1.20-2.86).ConclusionsThe accuracy of the model is affected by the classification chosen and the topic of the message examined. When the vaccine debate is jostled by contested political decisions, tweet content becomes so heterogeneous that the accuracy of the model drops for less differentiated classes. However, our tests showed that it is possible to improve the accuracy by selecting tweets using a new method based on tweet length.

Exploring the Risk of Suicide in Real Time on Spanish Twitter: Observational Study.

BackgroundSocial media is now a common context wherein people express their feelings in real time. These platforms are increasingly showing their potential to detect the mental health status of the population. Suicide prevention is a global health priority and efforts toward early detection are starting to develop, although there is a need for more robust research.ObjectiveWe aimed to explore the emotional content of Twitter posts in Spanish and their relationships with severity of the risk of suicide at the time of writing the tweet.MethodsTweets containing a specific lexicon relating to suicide were filtered through Twitter's public application programming interface. Expert psychologists were trained to independently evaluate these tweets. Each tweet was evaluated by 3 experts. Tweets were filtered by experts according to their relevance to the risk of suicide. In the tweets, the experts evaluated: (1) the severity of the general risk of suicide and the risk of suicide at the time of writing the tweet (2) the emotional valence and intensity of 5 basic emotions; (3) relevant personality traits; and (4) other relevant risk variables such as helplessness, desire to escape, perceived social support, and intensity of suicidal ideation. Correlation and multivariate analyses were performed.ResultsOf 2509 tweets, 8.61% (n=216) were considered to indicate suicidality by most experts. Severity of the risk of suicide at the time was correlated with sadness (ρ=0.266; P<.001), joy (ρ=–0.234; P=.001), general risk (ρ=0.908; P<.001), and intensity of suicidal ideation (ρ=0.766; P<.001). The severity of risk at the time of the tweet was significantly higher in people who expressed feelings of defeat and rejection (P=.003), a desire to escape (P<.001), a lack of social support (P=.03), helplessness (P=.001), and daily recurrent thoughts (P=.007). In the multivariate analysis, the intensity of suicide ideation was a predictor for the severity of suicidal risk at the time (β=0.311; P=.001), as well as being a predictor for fear (β=–0.009; P=.01) and emotional valence (β=0.007; P=.009). The model explained 75% of the variance.ConclusionsThese findings suggest that it is possible to identify emotional content and other risk factors in suicidal tweets with a Spanish sample. Emotional analysis and, in particular, the detection of emotional variations may be key for real-time suicide prevention through social media.

Exploring the extent of digitalisation and digital diplomacy in Pakistan embassies

ABSTRACT This study examines Pakistan embassies' social media adoption, use, and level of public engagement in relation to ‘networked public diplomacy'. Web surveying showed that majority of the embassies have accounts on social networking sites, but some are inactive. The manual content and thematic analysis of tweets (n = 490) collected during December 2019 from the Twitter accounts of five Pakistan embassies revealed considerable differences in the number, regularity and frequency of the posts; but showed similarity in the message content disseminated by the embassies. The results also demonstrated that the embassies generally follow state-centric informative and one-way communication strategies, with the exception of one embassy that somewhat engaged its audience through Twiplomacy. A key finding showed that embassies in places with fewer diaspora are more effective in producing messages that encourage dialogic communication compared with embassies with a larger expat population. In addition, results from user profile analysis of the accounts’ followers suggested a limited digital presence of Pakistani missions among the foreign netizens. In general, the findings showed that Pakistan embassies are present on social media sites, but lack the inclination to communicate dialogically in real time and to show reasonable presence among digital audiences.

IMPLEMENTASI ALGORITMA FUZZY C-MEANS DAN FUZZY POSSIBILISTICS C-MEANS UNTUK KLASTERISASI DATA TWEETS PADA AKUN TWITTER TOKOPEDIA

Social media has become the most popular media, which can be accessed by young to old age. Twitter became one of the effective media and the familiar one used by the public, thus making the company make Twitter one of the promotional tools, one of which is Tokopedia. The research aims to group tweets uploaded by @tokopedia Twitter accounts based on the type of tweets content that gets a lot of retweets and likes by followers of @tokopedia. Application of text mining to cluster tweets on the @tokopedia Twitter account using Fuzzy C-Means and Fuzzy Possibilistic C-Means algorithms that viewed the accuracy comparison of both methods used the Modified Partition Coefficient (MPC) cluster validity. The clustering process was carried out five times by the number of clusters ranging from 3 to 7 clusters. The results of the study showed the Fuzzy C-Means method is a better method compared to the Fuzzy Possibilistic C-Means method in clustering data tweets, with the number of clusters formed is 4. The content type formed is related to promo, discount, cashback, prize quizzes, and event promotions organized by Tokopedia. Content with the highest average number of retweets and likes is about automotive deals, sports tools, and merchandise offerings. So, that PT Tokopedia can use this content type as a tool for advertising on Twitter because it gets more likes by followers of @tokopedia.Keywords: Data Tweets, Clustering, Fuzzy C-Means, Fuzzy Possibilistics C-Means, Modified Partition Coefficient.

Cognitive Networks Extract Insights on COVID-19 Vaccines from English and Italian Popular Tweets: Anticipation, Logistics, Conspiracy and Loss of Trust

Monitoring social discourse about COVID-19 vaccines is key to understanding how large populations perceive vaccination campaigns. This work reconstructs how popular and trending posts framed semantically and emotionally COVID-19 vaccines on Twitter. We achieve this by merging natural language processing, cognitive network science and AI-based image analysis. We focus on 4765 unique popular tweets in English or Italian about COVID-19 vaccines between December 2020 and March 2021. One popular English tweet contained in our data set was liked around 495,000 times, highlighting how popular tweets could cognitively affect large parts of the population. We investigate both text and multimedia content in tweets and build a cognitive network of syntactic/semantic associations in messages, including emotional cues and pictures. This network representation indicates how online users linked ideas in social discourse and framed vaccines along specific semantic/emotional content. The English semantic frame of “vaccine” was highly polarised between trust/anticipation (towards the vaccine as a scientific asset saving lives) and anger/sadness (mentioning critical issues with dose administering). Semantic associations with “vaccine,” “hoax” and conspiratorial jargon indicated the persistence of conspiracy theories and vaccines in extremely popular English posts. Interestingly, these were absent in Italian messages. Popular tweets with images of people wearing face masks used language that lacked the trust and joy found in tweets showing people with no masks. This difference indicates a negative effect attributed to face-covering in social discourse. Behavioural analysis revealed a tendency for users to share content eliciting joy, sadness and disgust and to like sad messages less. Both patterns indicate an interplay between emotions and content diffusion beyond sentiment. After its suspension in mid-March 2021, “AstraZeneca” was associated with trustful language driven by experts. After the deaths of a small number of vaccinated people in mid-March, popular Italian tweets framed “vaccine” by crucially replacing earlier levels of trust with deep sadness. Our results stress how cognitive networks and innovative multimedia processing open new ways for reconstructing online perceptions about vaccines and trust.

LOCATION PREDICTION ON TWITTER USING MACHINE LEARNING TECHNIQUES

These days, location prediction of users using online social media generates a lot of research. For decades, researchers have looked on automatic location recognition in relation to or referenced in documents. As one of the most popular online social networking sites, Twitter has attracted a large number of users who send millions of tweets on a regular basis. Because of the global reach of its users and the constant flow of messages, location prediction on Twitter has gotten a lot of attention lately. Tweets, brief, noisy, and rich-natured communications, provide numerous study hurdles to researchers. A general picture of location prediction using tweets is investigated in the suggested framework. Tweet location, in particular, is anticipated based on tweet content. It is very important to outline tweet content and situations highlighted how the difficulties are dependent on certain text inputs. Here, we apply machine learning techniques like as naive bayes, Support Vector Machines, and Decision Trees to estimate the user's location from tweet content.

The popularity of contradictory information about COVID-19 vaccine on social media in China

To eliminate the impact of contradictory information on vaccine hesitancy on social media, this research developed a framework to compare the popularity of information expressing contradictory attitudes towards COVID-19 vaccine or vaccination, mine the similarities and differences among contradictory information's characteristics, and determine which factors influenced the popularity mostly. We called Sina Weibo API to collect data. Firstly, to extract multi-dimensional features from original tweets and quantify their popularity, content analysis, sentiment computing and k-medoids clustering were used. Statistical analysis showed that anti-vaccine tweets were more popular than pro-vaccine tweets, but not significant. Then, by visualizing the features' centrality and clustering in information-feature networks, we found that there were differences in text characteristics, information display dimension, topic, sentiment, readability, posters' characteristics of the original tweets expressing different attitudes. Finally, we employed regression models and SHapley Additive exPlanations to explore and explain the relationship between tweets' popularity and content and contextual features. Suggestions for adjusting the organizational strategy of contradictory information to control its popularity from different dimensions, such as poster's influence, activity and identity, tweets' topic, sentiment, readability were proposed, to reduce vaccine hesitancy.

Information sharing practices during the COVID-19 pandemic: A case study about face masks.

This article contributes an empirical analysis of information sharing practices on Twitter relating to the use of face masks in the context of COVID-19. Behavioural changes, such as the use of face masks, are often influenced by people's knowledge and perceptions, which in turn can be affected by the information available to them. Face masks were not recommended for use by the UK public at the beginning of the COVID-19 pandemic. Due to developments in scientific understanding, the guidance changed and by the end of 2020 they were mandatory on public transport and in shops. This research examines tweets in this longitudinal context and, therefore, provides novel insights into the dynamics of crisis communication in an ongoing crisis event with emerging scientific evidence. Specifically, analysis of the content of tweets, external resources most frequently shared, and users sharing information are considered. The conclusions contribute to developing understanding of the digital information ecology and provide practical insights for crisis communicators. Firstly, the analysis shows changes in the frequency of tweets about the topic correspond with key guidance and policy changes. These are, therefore, points in time official channels of information need to utilise the public's information seeking and sharing practices. Secondly, due to changes in face mask guidance and policy, the current literature on digital information ecology is insufficient for capturing the dynamic nature of a long-term ongoing crisis event. Challenges can arise due to the prolonged circulation of out-of-date information, i.e. not strategic misinformation, nor "mis"-information at all, which can have serious ramifications for crisis communication practitioners. Thirdly, the role of traditional media and other journalism/broadcasting platforms in shaping conversations is evident, as is the potential for scientific organisations' and individual people's Twitter user accounts. This plurality of contributors needs to be acknowledged and understood to inform crisis communication strategies.

Twitter account classification using account metadata: organizationvs. individual

Organizations present their existence on social media to gain followers and reach out to the crowds. Social media-related tasks and applications, such as social media graph construction, sentiment analysis, and bot detection, are required to identify the entities' account types. Some applications focus on personal accounts, whereas others only need nonpersonal accounts. This paper addresses the account classification problem using only minimum amount of data, which is the metadata of the account's profile. The proposed approach classifies accounts either as organization or individual, in a language-independent manner, without collecting the accounts' tweet content. The model uses a long short term memory (LSTM) network for processing the textual properties and a fully-connected neural network for processing the numerical features. We apply our solution to a collection of Twitter accounts, as it is one of the most widely used social networks. Our classifier, based solely on the account metadata, achieves an average of 97.4% accuracy under 7-fold cross-validation. The experiments show that the account metadata is a qualified resource for accurately estimating the account types.

#ColonCancer: Social Media Discussions About Colorectal Cancer During the COVID-19 Pandemic.

Colorectal cancer (CRC) is the second leading cause of cancer-related mortality worldwide. Social media platforms such as Twitter are extensively used to communicate about cancer care, yet little is known about the role of these online platforms in promoting early detection or sharing the lived experiences of patients with CRC. This study tracked Twitter discussions about CRC and characterized participating users to better understand public communication and perceptions of CRC during the COVID-19 pandemic. Tweets containing references to CRC were collected from January 2020 to April 2021 using Twitter's Application Programming Interface. Account metadata was used to predict user demographic information and classify users as either organizations, individuals, clinicians, or influencers. We compared the number of impressions across users and analyzed the content of tweets using natural language processing models to identify prominent topics of discussion. There were 72,229 unique CRC-related tweets by 31,170 users. Most users were male (66%) and older than 40 years (57%). Individuals accounted for most users (44%); organizations (35%); clinicians (19%); and influencers (2%). Influencers made the most median impressions (35,853). Organizations made the most overall impressions (1,067,189,613). Tweets contained the following topics: bereavement (20%), appeals for early detection (20%), research (17%), National Colorectal Cancer Awareness Month (15%), screening access (14%), and risk factors (14%). Discussions about CRC largely focused on bereavement and early detection. Online coverage of National Colorectal Cancer Awareness Month and personal experiences with CRC effectively stimulated goal-oriented tweets about early detection. Our findings suggest that although Twitter is commonly used for communicating about CRC, partnering with influencers may be an effective strategy for improving communication of future public health recommendations related to CRC.

Alih Kode dan Campur Kode Pada Akun Twitter @Marnombois

The problem reviewed in the research is alluding to code-switching and code-mixing on Twitter social media, along with the factors causing code-switching and code-mixing. The aim is to identify the form of code-switching and code-mixing in the @marnombois account tweets on Twitter social media using qualitative research. The data is taken from screenshots on tweet content that is following the title of the researcher. With qualitative research methods. The alteration of Javanese to Indonesian and Javanese to foreign languages is influenced by the user's background and several other social factors.

Analysis of Content, Social Networks, and Sentiment of Front-of-Pack Nutrition Labeling in the European Union on Twitter.

In recent years, concerted political efforts have been made at the national and European Union (EU) level to promote the consumption of healthy foods. The European Commission (EC) expressed the need for a harmonized and mandatory front-of-pack nutrition labeling (FOPL) system at the EU level. The EC will adopt the proposal by the end of 2022. Our research work aims to understand the public discourse on FOPL in the EU via Twitter, by analyzing tweet content, sentiment, and mapping network characteristics. Tweet search and data collection were performed using the Twitter application programming interface (API), with no time or language restrictions. The content was coded with the QRS Nvivo software package and analyzed thematically. Automatic sentiment analysis was performed with QSR Nvivo, and network analysis was performed with Gephi 0.9.2. A total of 4,073 tweets were posted, mostly from the UK, Spain, and France. Themes that have emerged from the discussion on Twitter include the types of food labeling, food industry, healthy vs. unhealthy foods in the context of food labeling, EU regulation, political conflicts, and science and education. Nutri-Score dominated the discussion on Twitter. General topics were perceived negatively by Twitter users with more positive sentiments toward the food industry, while negative sentiments were observed toward the discourse of political conflicts. The network analysis showed that a centralized communication was hardly existed between countries. Our results reveal that the discussion of FOPL on Twitter is limited to a very limited group of people, and it seems necessary to inform a wide range of consumers about existing and upcoming FOPL schemes. Educational programs should empower consumers to understand what a healthy diet is and how it relates to FOPL, regardless of the existing labeling system.

Evaluating Jokowi's Policy on Alcoholic Drink Investment in Indonesia by using sentiment analysis

This paper discusses the evaluation of Jokowi's policy regarding alcoholic drink investment in Indonesia by using sentiment analysis. The source of data used as policy feedback in this study is data from the Twitter API. There were 6,963 tweets taken five days before and five days after Jokowi lifted the policy. The data was then manually annotated as many as 963 tweets by sentiment labels. This study uses NLP Techniques to process the data and uses SVM to classify it. Furthermore, using trained data, this paper labels the rest of the tweets into three groups of sentiments, namely positive, negative, and neutral, to see how much public support or rejection of policies on social media. From the analysis, the alcoholic drink investment policy was not successful. The number of negative sentiments from the public shows that this policy is against the people's will. Negative comments dominated during the period of this study, significantly before the President lifted the policy. Nevertheless, Jokowi's decision to revoke the alcohol investment permit is the right step and has succeeded in reducing negative comments and rejections on social media, especially Twitter. This paper also covers words that are interconnected and related in Twitter to give an overview of the tweet's contents. Before the policy was revoked, many tweets contained a rejection of Jokowi's policies, rejection of the Papuan government, and asked the MUI to suggest Jokowi revoke this policy. After the policy was revoked, the comments were more directed at criticism of the President's attitude, which stated that he hated foreign products but allowed investment in alcohol and had made policies that provoked a public controversy.

FREEDOM: Effective Surveillance and Investigation of Water-borne Diseases from Data-centric Networking Using Machine Learning Techniques

Worldwide, epidemics continue to be a concern on public health. Even with the technological advances, there are still barriers present in predicting the outbreaks. We propose a new methodology known as FREEDOM (Effective Surveillance and Investigation of Water-borne Diseases from data-centric networking using Machine Learning) to perform effective surveillance and investigation of water-borne diseases from social media with next-generation data. In the proposed model, we collected the data from the Twitter media, preprocessed the tweet content, performed hierarchical spectral clustering, and generated the frequent word set from each cluster through the apriori algorithm. At last, the inferences are extracted from the frequent word set through human intervention. From the experimental results, the support and confidence value of the outcome derived from the Apriori algorithm has exhibited the different water-borne diseases that are not listed in the WHO (World Health Organization), and the surveillance of those diseases with percentage ranking and has been achieved using the data-centric networking. They get aligned with precise results portraying real statistics. This type of analysis will empower doctors and health organizations (Government sector) to keep track of the water-borne diseases, their symptoms for early detection, and safe recovery thereby sufficiently reducing the death tolls.

Analyzing sentiments and themes on cannabis in Canada using 2018 to 2020 Twitter data

IntroductionThe Canadian Cannabis Act came into effect on October 17, 2018, which allowed Canadian adults to consume cannabis for non-medical purposes (Government of Canada, Cannabis regulations (SOR/2018-144). Cannabis Act, (2018a); Parliament of Canada, C-45: an Act respecting cannabis and to amend the Controlled Drugs and Substances Act, the Criminal Code and other Acts, 2018). With this major policy change, it is unknown how the attitude of the public changed and how information on cannabis changed. Social media platforms, including Twitter, are significant venues for studying emerging patterns in social issues such as cannabis legalization. This study aimed to examine sentiments, themes and contents of cannabis-related tweets by suppliers (both licensed and unlicensed) and general tweets in Canada. To our knowledge, this is the first analysis that mixes sentiment analysis and thematic analysis of Canadians’ cannabis-related Twitter data.MethodA sample of Canadian cannabis-related tweets was collected from January 2018 to August 2020 through the Twitter Application Programming Interface (API). Using a standard access token and the Twitter Standard Search API, tweets were extracted based on Twitter handles to capture the content of both licensed and unlicensed cannabis retailers in Canada, as well as relevant cannabis-related keywords to capture public content. We conducted sentiment and positive polarity analyses, and content analysis to identify attitudes and themes around cannabis use in Canada.ResultsThis study gathered and analyzed a total of 44,970 tweets in the sentiment analysis and a total of 1035 tweets in the thematic analysis. Descriptive analysis showed that monthly tweets peaked prior to legalization in October 2018 and again during the initial wave of the COVID-19 pandemic in February and March 2020. The data showed an overall positive sentiment polarity with a high of + 0.24 in April 2019 and a low of + 0.14 in March 2020.Thematic analysis revealed the themes: (i) education/information, (ii) uses of cannabis, (iii) cannabis products including packing, quality, price, types, and sources, (iv) cannabis policies including regulations and public safety, (v) access, (vi) social issues include gender and stigma, and (vii) COVID-19 impact.ConclusionThis study combined the power of big data collection and analysis with manual coding and analysis methods to extract rich content from large data using social media communications on issues related to cannabis in Canada. The findings of this study may inform policies on advertising cannabis products and highlighted some patterns related to education, access, and safety that deserve further investigation.