Using Twitter Data and Sentiment Analysis to Study Diseases Dynamics

Carchiolo, Vincenza; Longheu, Alessandro; Malgeri, Michele

doi:10.1007/978-3-319-22741-2_2

Cited by 28 publications

(14 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among them, the prominent work of de Bie [30] defines a general and statistically-founded framework of exploratory data analysis. Information theory is used to formalize the subjective interest as the divergence to prior belief; (2) The approaches that integrate user feedback interactively during the mining task [31][32][33]; (3) The methods which aim to learn an explicit model of user interests [34] and rank patterns in post-processing [35]. There is no approach in the literature that detects userdriven events.…”

Section: Related Workmentioning

confidence: 99%

“…Social media data have been analysed for several purposes, e.g. to understand the concerns of a population [1], study disease dynamics [2], or predict real-world outcomes [3].…”

Section: Introductionmentioning

confidence: 99%

“…This paper responds to these concerns by (1) proposing efficient algorithms to detect geolocated events and (2) integrating user interests into the extraction process through interactions with the system. This is the first attempt to the discovery of user-driven events.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

User-driven geolocated event detection in social media

Bendimerad

Plantevit

Robardet

et al. 2019

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Event detection is one of the most important research topics in social media analysis. Despite this interest, few researchers have addressed the problem of identifying geolocated events in an unsupervised way, and none includes user interests during the process. In this paper, we tackle the problem of local event detection from social media data. We present a method to automatically identify events by evaluating the burstiness of hashtags in a geographical area and a time interval, and at the same time integrating user feedback. We devise two algorithms to discover user-driven events. The first one relies on an exact enumeration process, while the other directly samples the space of events. In our empirical study, we provide evidence that geolocated events cannot be detected by non location-aware methods. We also show that our methods (i) outperform by a factor of two to several orders of magnitude state-of-the-art methods designed to discover geolocated events, (ii) are more robust to noise, (iii) and produce high quality events with respect to user interests.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Social media data have been analysed for several purposes, e.g. to understand the concerns of a population [1], study disease dynamics [2], or predict real-world outcomes [3].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

User-driven geolocated event detection in social media

Bendimerad

Plantevit

Robardet

et al. 2019

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

show abstract

“…In fact, when structured data is stored in an EHR, it is desirable to support automated systems at the point of care, and to help physicians in diagnosis. These studies endorsed most NLP applications in the medical field; for instance, those concerning the use of Twitter data and sentiment analysis to study diseases dynamics [3], or [4], where the correlation among "stress", "insomnia", and "headache" is analysed. In the field of medical application, the image processing are very useful in EHR data manipulation [5] [6], where medical images play an important role in particular to help physicians to monitor the evolution of complex pathologies [7].…”

Section: Introductionmentioning

confidence: 99%

Medical prescription classification: a NLP-based approach

Carchiolo¹,

Longheu²,

Reitano³

et al. 2019

Proceedings of the 2019 Federated Conference on Computer Science and Information Systems

Self Cite

View full text Add to dashboard Cite

The digitization of healthcare data has been consolidated in the last decade as a must to manage the vast amount of data generated by healthcare organizations. Carrying out this process effectively represents an enabling resource that will improve healthcare services provision, as well as on-the-edge related applications, ranging from clinical text mining to predictive modelling, survival analysis, patient similarity, genetic data analysis and many others. The application presented in this work concerns the digitization of medical prescriptions, both to provide authorization for healthcare services or to grant reimbursement for medical expenses. The proposed system first extract text from scanned medical prescription, then Natural Language Processing and machine learning techniques provide effective classification exploiting embedded terms and categories about patient/doctor personal data, symptoms, pathology, diagnosis and suggested treatments. A REST ful Web Service is introduced, together with results of prescription classification over a set of 800K+ of diagnostic statements.

show abstract

“…Sentiment analysis involves in mining the naturally expressed text to understand the feeling of people towards the entity of interest. Sentiment mining and analysis has found many application in areas of healthcare [3], [4], tourism [5], fraud detection [6], finance [7], politics [8], business [9], few more applications are listed in [10]. In [11] informatics, theoretic approach is used for classification of sentiments.…”

Section: Introductionmentioning

confidence: 99%

3D Visualization of Sentiment Measures and Sentiment Classification using Combined Classifier for Customer Product Reviews

Urologin¹,

Thomas²

2018

ijacsa

View full text Add to dashboard Cite

Abstract-TheInternet has wide reachability making many users to buy the products online using e-commerce websites. Usually, users provide their opinions, comments, and reviews about the products in social media, e-commerce websites, blogs, etc. The product review comments provided by the customers have rich information about the usage of the products they bought and their sentiments towards those products. In this research, we have collected reviews from Amazon.com and performed sentiment analysis to collect sentiment information. We have proposed 3D visualizations to represent sentiment information, such as sentiment scores and statistics about words used in the reviews. The 3D visualizations are useful to represent large sentiment related information and to have an in-depth understanding of sentiments of users. We have developed a combined classifier using Logistic Regression, Decision Tree and Support Vector Machine. From the reviews, we formed N-gram features using a bag of words and performed sentiment classification using combined classifier. On 10 fold crossvalidation, a maximum classification rate for combined classifier of 90.22% is obtained for sentiment classification.

show abstract

Using Twitter Data and Sentiment Analysis to Study Diseases Dynamics

Cited by 28 publications

References 19 publications

User-driven geolocated event detection in social media

User-driven geolocated event detection in social media

Medical prescription classification: a NLP-based approach

3D Visualization of Sentiment Measures and Sentiment Classification using Combined Classifier for Customer Product Reviews

Contact Info

Product

Resources

About