scholarly journals Utilizing deep learning and graph mining to identify drug use on Twitter data

2020 ◽  
Vol 20 (S11) ◽  
Author(s):  
Joseph Tassone ◽  
Peizhi Yan ◽  
Mackenzie Simpson ◽  
Chetan Mendhe ◽  
Vijay Mago ◽  
...  
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Graph Mining ◽  
Predictive Capability ◽  
Rule Mining ◽  
Twitter Data ◽  
Practical Usefulness ◽  
Positive Classification ◽  
And Behavior ◽  
Media Data

Abstract Background The collection and examination of social media has become a useful mechanism for studying the mental activity and behavior tendencies of users. Through the analysis of a collected set of Twitter data, a model will be developed for predicting positively referenced, drug-related tweets. From this, trends and correlations can be determined. Methods Social media data (tweets and attributes) were collected and processed using topic pertaining keywords, such as drug slang and use-conditions (methods of drug consumption). Potential candidates were preprocessed resulting in a dataset of 3,696,150 rows. The predictive classification power of multiple methods was compared including SVM, XGBoost, BERT and CNN-based classifiers. For the latter, a deep learning approach was implemented to screen and analyze the semantic meaning of the tweets. Results To test the predictive capability of the model, SVM and XGBoost were first employed. The results calculated from the models respectively displayed an accuracy of 59.33% and 54.90%, with AUC’s of 0.87 and 0.71. The values show a low predictive capability with little discrimination. Conversely, the CNN-based classifiers presented a significant improvement, between the two models tested. The first was trained with 2661 manually labeled samples, while the other included synthetically generated tweets culminating in 12,142 samples. The accuracy scores were 76.35% and 82.31%, with an AUC of 0.90 and 0.91. Using association rule mining in conjunction with the CNN-based classifier showed a high likelihood for keywords such as “smoke”, “cocaine”, and “marijuana” triggering a drug-positive classification. Conclusion Predictive analysis with a CNN is promising, whereas attribute-based models presented little predictive capability and were not suitable for analyzing text of data. This research found that the commonly mentioned drugs had a level of correspondence with frequently used illicit substances, proving the practical usefulness of this system. Lastly, the synthetically generated set provided increased accuracy scores and improves the predictive capability.

Utilizing Twitter Data Analysis and Deep Learning to Identify Drug Use (Preprint)

2019 ◽  
Author(s):  
Joseph Tassone ◽  
Peizhi Yan ◽  
Mackenzie Simpson ◽  
Chetan Mendhe ◽  
Vijay Mago ◽  
...  
Keyword(s):  
Social Media ◽  
Logistic Regression ◽  
Deep Learning ◽  
Decision Tree ◽  
Semantic Meaning ◽  
Predictive Capability ◽  
Logistic Regression Models ◽  
Twitter Data ◽  
Data Points ◽  
Positive Classification

BACKGROUND The collection and examination of social media has become a useful mechanism for studying the mental activity and behavior tendencies of users. OBJECTIVE Through the analysis of a collected set of Twitter data, a model will be developed for predicting positively referenced, drug-related tweets. From this, trends and correlations can be determined. METHODS Twitter social media tweets and attribute data were collected and processed using topic pertaining keywords, such as drug slang and use-conditions (methods of drug consumption). Potential candidates were preprocessed resulting in a dataset 3,696,150 rows. The predictive classification power of multiple methods was compared including regression, decision trees, and CNN-based classifiers. For the latter, a deep learning approach was implemented to screen and analyze the semantic meaning of the tweets. RESULTS The logistic regression and decision tree models utilized 12,142 data points for training and 1041 data points for testing. The results calculated from the logistic regression models respectively displayed an accuracy of 54.56% and 57.44%, and an AUC of 0.58. While an improvement, the decision tree concluded with an accuracy of 63.40% and an AUC of 0.68. All these values implied a low predictive capability with little to no discrimination. Conversely, the CNN-based classifiers presented a heavy improvement, between the two models tested. The first was trained with 2,661 manually labeled samples, while the other included synthetically generated tweets culminating in 12,142 samples. The accuracy scores were 76.35% and 82.31%, with an AUC of 0.90 and 0.91. Using association rule mining in conjunction with the CNN-based classifier showed a high likelihood for keywords such as “smoke”, “cocaine”, and “marijuana” triggering a drug-positive classification. CONCLUSIONS Predictive analysis without a CNN is limited and possibly fruitless. Attribute-based models presented little predictive capability and were not suitable for analyzing this type of data. The semantic meaning of the tweets needed to be utilized, giving the CNN-based classifier an advantage over other solutions. Additionally, commonly mentioned drugs had a level of correspondence with frequently used illicit substances, proving the practical usefulness of this system. Lastly, the synthetically generated set provided increased scores, improving the predictive capability. CLINICALTRIAL None

scholarly journals What Your Tweets Tell Us About You: Identity, Ownership and Privacy of Twitter Data

2012 ◽  
Vol 7 (1) ◽  
pp. 174-197 ◽  
Author(s):  
Heather Small ◽  
Kristine Kasianovitz ◽  
Ronald Blanford ◽  
Ina Celaya
Keyword(s):  
Social Media ◽  
Social Networking Sites ◽  
Data Sets ◽  
Data Set ◽  
Social Media Data ◽  
Twitter Data ◽  
Other Information ◽  
Rich Data ◽  
Additional Value ◽  
Media Data

Social networking sites and other social media have enabled new forms of collaborative communication and participation for users, and created additional value as rich data sets for research. Research based on accessing, mining, and analyzing social media data has risen steadily over the last several years and is increasingly multidisciplinary; researchers from the social sciences, humanities, computer science and other domains have used social media data as the basis of their studies. The broad use of this form of data has implications for how curators address preservation, access and reuse for an audience with divergent disciplinary norms related to privacy, ownership, authenticity and reliability.In this paper, we explore how the characteristics of the Twitter platform, coupled with an ambiguous and evolving understanding of privacy in networked communication, and divergent disciplinary understandings of the resulting data, combine to create complex issues for curators trying to ensure broad-based and ethical reuse of Twitter data. We provide a case study of a specific data set to illustrate how data curators can engage with the topics and questions raised in the paper. While some initial suggestions are offered to librarians and other information professionals who are beginning to receive social media data from researchers, our larger goal is to stimulate discussion and prompt additional research on the curation and preservation of social media data.

Changing Trends in Long-Term Sentiments and Neighborhood Determinants in a Shrinking City

2021 ◽  
pp. 0739456X2110442
Author(s):  
Yunmi Park ◽  
Minju Kim ◽  
Jiyeon Shin ◽  
Megan E. Heim LaFrombois
Keyword(s):  
Social Media ◽  
Built Environment ◽  
Urban Regeneration ◽  
Neighborhood Conditions ◽  
Social Media Data ◽  
Twitter Data ◽  
Changing Trends ◽  
Shrinking City ◽  
Media Data

This research examined social media’s role in understanding perceptions about the spaces in which individuals interact, what planners can learn from social media data, and how to use social media to inform urban regeneration efforts. Using Twitter data from 2010 to 2018 recorded in one U.S. shrinking city, Detroit, Michigan, this paper longitudinally investigated topics that people discuss, their emotions, and neighborhood conditions associated with these topics and sentiments. Findings demonstrate that neighborhood demographics, socioeconomic, and built environment conditions impact people’s sentiments.

scholarly journals Sentiment Analysis Of Twitter Data By Using Deep Learning And Machine Learning

2021 ◽  
Vol 12 (6) ◽  
pp. 962-970
Author(s):  
Prof. Manisha Sachin Dabade, Et. al.
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Daily Monitoring ◽  
Fine Grain ◽  
Large Size ◽  
Twitter Data ◽  
The Social ◽  
Enormous Amount

In today’s world, social media is viral and easily accessible. The Social media sites like Twitter, Facebook, Tumblr, etc. are a primary and valuable source of information.Twitter is a micro-blogging platform, and it provides an enormous amount of data. Such type of information can use for different sentiment analysis applications such as reviews, predictions, elections, marketing, etc. It is one of the most popular sites where peoples write tweets, retweets, and interact daily. Monitoring and analyzing these tweets give valuable feedback to users. Due to this data's large size, sentiment analysis is using to analyze this data without going through millions of tweets manually. Any user writes their reviews about different products, topics, or events on Twitter, called tweets and retweets. People also use emojis such as happy, sad, and neutral in expressing their emotions, so these sites contain expansive volumes of unprocessed data called raw data. The main goal of this research is to recognize the algorithms by using Machine Learning Classifiers. The study intends to categorize Fine-grain sentiments within Tweets of Vaccination (89974 tweets) through machine learning and a deep learning approach. The study takes consideration of both labeled and unlabeled data. It also detects emojis from tweets using machine learning libraries like Textblob, Vadar, Fast text, Flair, Genism, spaCy, and NLTK.

scholarly journals A Comprehensive Analysis of Approaches for Sentiment Analysis Using Twitter Data on COVID-19 Vaccines

2021 ◽  
Vol 2 (2) ◽  
pp. 1-10
Author(s):  
Amrita Mishra ◽  
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Sentiment Analysis ◽  
Text Classification ◽  
Comprehensive Analysis ◽  
Social Media Data ◽  
The Public ◽  
Opinion Analysis ◽  
Twitter Data ◽  
Media Data

Sentiment Analysis has paved routes for opinion analysis of masses over unrestricted territorial limits. With the advent and growth of social media like Twitter, Facebook, WhatsApp, Snapchat in today’s world, stakeholders and the public often takes to expressing their opinion on them and drawing conclusions. While these social media data are extremely informative and well connected, the major challenge lies in incorporating efficient Text Classification strategies which not only overcomes the unstructured and humongous nature of data but also generates correct polarity of opinions (i.e. positive, negative, and neutral). This paper is a thorough effort to provide a brief study about various approaches to SA including Machine Learning, Lexicon Based, and Automatic Approaches. The paper also highlights the comparison of positive, negative, and neutral tweets of the Sputnik V, Moderna, and Covaxin vaccines used for preventive and emergency use of COVID-19 disease.

scholarly journals SPATIAL-TEMPORAL ANALYSIS OF SOCIAL MEDIA DATA RELATED TO NEPAL EARTHQUAKE 2015

2016 ◽  
Vol XLI-B2 ◽  
pp. 567-571
Author(s):  
L. Thapa
Keyword(s):  
Social Media ◽  
Temporal Analysis ◽  
Archaeological Sites ◽  
Social Media Data ◽  
User Input ◽  
Nepal Earthquake ◽  
Twitter Data ◽  
The Social ◽  
Media Data ◽  
Spatial Temporal Analysis

Social Medias these days have become the instant communication platform to share anything; from personal feelings to the matter of public concern, these are the easiest and aphoristic way to deliver information among the mass. With the development of Web 2.0 technologies, more and more emphasis has been given to user input in the web; the concept of Geoweb is being visualized and in the recent years, social media like Twitter, Flicker are among the popular Location Based Social Medias with locational functionality enabled in them. Nepal faced devastating earthquake on 25 April, 2015 resulting in the loss of thousands of lives, destruction in the historical-archaeological sites and properties. Instant help was offered by many countries around the globe and even lots of NGOs, INGOs and people started the rescue operations immediately; concerned authorities and people used different communication medium like Frequency Modulation Stations, Television, and Social Medias over the World Wide Web to gather information associated with the Quake and to ease the rescue activities. They also initiated campaign in the Social Media to raise the funds and support the victims. Even the social medias like Facebook, Twitter, themselves announced the helping campaign to rebuild Nepal. In such scenario, this paper features the analysis of Twitter data containing hashtag related to Nepal Earthquake 2015 together with their temporal characteristics, when were the message generated, where were these from and how these spread spatially over the internet?

scholarly journals Linking Twitter and survey data: asymmetry in quantity and its impact

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Tarek Al Baghal ◽  
Alexander Wenz ◽  
Luke Sloan ◽  
Curtis Jessop
Keyword(s):  
Social Media ◽  
Survey Data ◽  
Linked Data ◽  
Social Research ◽  
Data Sources ◽  
Social Media Data ◽  
Twitter Data ◽  
Unique Source ◽  
Methodological Aspects ◽  
Media Data

AbstractLinked social media and survey data have the potential to be a unique source of information for social research. While the potential usefulness of this methodology is widely acknowledged, very few studies have explored methodological aspects of such linkage. Respondents produce planned amounts of survey data, but highly variant amounts of social media data. This study explores this asymmetry by examining the amount of social media data available to link to surveys. The extent of variation in the amount of data collected from social media could affect the ability to derive meaningful linked indicators and could introduce possible biases. Linked Twitter data from respondents to two longitudinal surveys representative of Great Britain, the Innovation Panel and the NatCen Panel, show that there is indeed substantial variation in the number of tweets posted and the number of followers and friends respondents have. Multivariate analyses of both data sources show that only a few respondent characteristics have a statistically significant effect on the number of tweets posted, with the number of followers being the strongest predictor of posting in both panels, women posting less than men, and some evidence that people with higher education post less, but only in the Innovation Panel. We use sentiment analyses of tweets to provide an example of how the amount of Twitter data collected can impact outcomes using these linked data sources. Results show that more negatively coded tweets are related to general happiness, but not the number of positive tweets. Taken together, the findings suggest that the amount of data collected from social media which can be linked to surveys is an important factor to consider and indicate the potential for such linked data sources in social research.

Deep Learning Method for Prediction of DDoS Attacks on Social Media

2019 ◽  
Vol 11 (01n02) ◽  
pp. 1950002
Author(s):  
Rasim M. Alguliyev ◽  
Ramiz M. Aliguliyev ◽  
Fargana J. Abdullayeva
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Social Networking ◽  
Cyber Attacks ◽  
Test Accuracy ◽  
Learning Method ◽  
Ddos Attacks ◽  
Twitter Data ◽  
Social Events

Recently, data collected from social media enable to analyze social events and make predictions about real events, based on the analysis of sentiments and opinions of users. Most cyber-attacks are carried out by hackers on the basis of discussions on social media. This paper proposes the method that predicts DDoS attacks occurrence by finding relevant texts in social media. To perform high-precision classification of texts to positive and negative classes, the CNN model with 13 layers and improved LSTM method are used. In order to predict the occurrence of the DDoS attacks in the next day, the negative and positive sentiments in social networking texts are used. To evaluate the efficiency of the proposed method experiments were conducted on Twitter data. The proposed method achieved a recall, precision, [Formula: see text]-measure, training loss, training accuracy, testing loss, and test accuracy of 0.85, 0.89, 0.87, 0.09, 0.78, 0.13, and 0.77, respectively.

scholarly journals Text based personality prediction from multiple social media data sources using pre-trained language model and model averaging

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Hans Christian ◽  
Derwin Suhartono ◽  
Andry Chowanda ◽  
Kamal Z. Zamli
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Extraction Method ◽  
Language Model ◽  
Model Averaging ◽  
Data Sources ◽  
Online Information ◽  
Social Media Data ◽  
Personality Prediction ◽  
Media Data

AbstractThe ever-increasing social media users has dramatically contributed to significant growth as far as the volume of online information is concerned. Often, the contents that these users put in social media can give valuable insights on their personalities (e.g., in terms of predicting job satisfaction, specific preferences, as well as the success of professional and romantic relationship) and getting it without the hassle of taking formal personality test. Termed personality prediction, the process involves extracting the digital content into features and mapping it according to a personality model. Owing to its simplicity and proven capability, a well-known personality model, called the big five personality traits, has often been adopted in the literature as the de facto standard for personality assessment. To date, there are many algorithms that can be used to extract embedded contextualized word from textual data for personality prediction system; some of them are based on ensembled model and deep learning. Although useful, existing algorithms such as RNN and LSTM suffers from the following limitations. Firstly, these algorithms take a long time to train the model owing to its sequential inputs. Secondly, these algorithms also lack the ability to capture the true (semantic) meaning of words; therefore, the context is slightly lost. To address these aforementioned limitations, this paper introduces a new prediction using multi model deep learning architecture combined with multiple pre-trained language model such as BERT, RoBERTa, and XLNet as features extraction method on social media data sources. Finally, the system takes the decision based on model averaging to make prediction. Unlike earlier work which adopts a single social media data with open and close vocabulary extraction method, the proposed work uses multiple social media data sources namely Facebook and Twitter and produce a predictive model for each trait using bidirectional context feature combine with extraction method. Our experience with the proposed work has been encouraging as it has outperformed similar existing works in the literature. More precisely, our results achieve a maximum accuracy of 86.2% and 0.912 f1 measure score on the Facebook dataset; 88.5% accuracy and 0.882 f1 measure score on the Twitter dataset.

Sign in / Sign up

Export Citation Format

Share Document