Hybrid System for Information Extraction from Social Media Text: Drug Abuse Case Study

Jenhani, Ferdaous; Gouider, Mohamed Salah; Saïd, Lamjed Ben

doi:10.1016/j.procs.2019.09.224

Cited by 9 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, a study proposed a multiple layer perceptron with a back propagation model to analyze and predict flu activities from real time data from Twitter [32]. In another study, researchers proposed a hybrid system to extract the salient features of drug abuse health-related tweets by applying linguistic patterns and machine learning classifiers [33].…”

Section: Twitter During Natural Disastersmentioning

confidence: 99%

Identifying and Characterizing the Propagation Scale of COVID-19 Situational Information on Twitter: A Hybrid Text Analytic Approach

et al. 2021

View full text Add to dashboard Cite

During the recent pandemic of COVID-19, an increasing amount of information has been propagated on social media. This situational information is valuable for public authorities. Therefore, this study characterized the propagation scale of situational information types by harnessing the power of natural language processing techniques and machine learning algorithms. We observed that the length of the post has a positive correlation with type 1 information (announcements), and negative words were mostly used in type 5 information (criticizing the government), whereas anxiety-related words have a negative effect on the amount of retweeted type 0 (precautions) and type 2 (donations) information. This type of research study not only contributes to the situational information literature by comprehensively defining categories but also provides data-oriented practical insights into information so that management authorities can formulate response strategies after the pandemic. Our approach is one of its kind and combines Twitter content features, user features and LIWC linguistic features with machine learning algorithms to analyze the propagation scale of situational information, and it achieved 77% accuracy with SVM while classifying the information categories.

show abstract

Section: Twitter During Natural Disastersmentioning

confidence: 99%

Identifying and Characterizing the Propagation Scale of COVID-19 Situational Information on Twitter: A Hybrid Text Analytic Approach

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The experimental results show that the model effectively extracts positive and negative sentiments from textual data and predicts future stock price movements. In another study,Jenhani et al [15] presented an ML model hybridized with a domain-based dictionary and linguistic rules for extracting drug abuse information from social media data (tweets). The learning model was trained and tested using 1,000,000 tweets from five different experimental settings.…”

Section: Introductionmentioning

confidence: 99%

“…However, ML methods struggle to handle massive amounts of highly complex data (e.g., complex compound texts, nested entities, and variety in data representation) [8], [11], [16]. For instance, Jenhani et al [15] noted that the volume, velocity, and variety issues of big data cannot be effectively managed by a simple implementation of the hybrid ML model.…”

Section: Introductionmentioning

confidence: 99%

Systematic Literature Review of Information Extraction From Textual Data: Recent Methods, Applications, Trends, and Challenges

et al. 2023

View full text Add to dashboard Cite

Information extraction (IE) is a challenging task, particularly when dealing with highly heterogeneous data. State-of-the-art data mining technologies struggle to process information from textual data. Therefore, various IE techniques have been developed to enable the use of IE for textual data. However, each technique differs from one another because it is designed for different data types and has different target information to be extracted. This study investigated and described the most contemporary methods for extracting information from textual data, emphasizing their benefits and shortcomings. To provide a holistic view of the domain, this comprehensive systematic literature review employed a systematic mapping process to summarize studies published in the last six years (from 2017 to 2022). It covers fundamental concepts, recent approaches, applications, and trends, in addition to challenges and future research prospects in this domain area. Based on an analysis of 161 selected studies, we found that the state-of-the-art models employ deep learning to extract information from textual data. Finally, this study aimed to guide novice and experienced researchers in future research and serve as a foundation for this research area.

show abstract

“…To demonstrate that the use of machine learning and linguistic rules separately is not enough to achieve better results for information extraction from social media, Jenhania et al [ 15 ] proposed a hybrid system combining dictionaries, linguistic patterns, and machine learning to extract structured and salient drug abuse information from health-related tweets. The results showed that the use of a linguistic method based on a dictionary with no dictionary updates is a failed solution.…”

Section: Introductionmentioning

confidence: 99%

Social Media Text Mining Framework for Drug Abuse: Development and Validation Study With an Opioid Crisis Case Analysis

Nasralah¹,

El‐Gayar²,

Wang³

2020

J Med Internet Res

View full text Add to dashboard Cite

Background Social media are considered promising and viable sources of data for gaining insights into various disease conditions and patients’ attitudes, behaviors, and medications. They can be used to recognize communication and behavioral themes of problematic use of prescription drugs. However, mining and analyzing social media data have challenges and limitations related to topic deduction and data quality. As a result, we need a structured approach to analyze social media content related to drug abuse in a manner that can mitigate the challenges and limitations surrounding the use of such data. Objective This study aimed to develop and evaluate a framework for mining and analyzing social media content related to drug abuse. The framework is designed to mitigate challenges and limitations related to topic deduction and data quality in social media data analytics for drug abuse. Methods The proposed framework started with defining different terms related to the keywords, categories, and characteristics of the topic of interest. We then used the Crimson Hexagon platform to collect data based on a search query informed by a drug abuse ontology developed using the identified terms. We subsequently preprocessed the data and examined the quality using an evaluation matrix. Finally, a suitable data analysis approach could be used to analyze the collected data. Results The framework was evaluated using the opioid epidemic as a drug abuse case analysis. We demonstrated the applicability of the proposed framework to identify public concerns toward the opioid epidemic and the most discussed topics on social media related to opioids. The results from the case analysis showed that the framework could improve the discovery and identification of topics in social media domains characterized by a plethora of highly diverse terms and lack of a commonly available dictionary or language by the community, such as in the case of opioid and drug abuse. Conclusions The proposed framework addressed the challenges related to topic detection and data quality. We demonstrated the applicability of the proposed framework to identify the common concerns toward the opioid epidemic and the most discussed topics on social media related to opioids.

show abstract

Hybrid System for Information Extraction from Social Media Text: Drug Abuse Case Study

Cited by 9 publications

References 12 publications

Identifying and Characterizing the Propagation Scale of COVID-19 Situational Information on Twitter: A Hybrid Text Analytic Approach

Identifying and Characterizing the Propagation Scale of COVID-19 Situational Information on Twitter: A Hybrid Text Analytic Approach

Systematic Literature Review of Information Extraction From Textual Data: Recent Methods, Applications, Trends, and Challenges

Social Media Text Mining Framework for Drug Abuse: Development and Validation Study With an Opioid Crisis Case Analysis

Contact Info

Product

Resources

About