Content analysis of pancreatic cancer conversations on Twitter: What matters most to users?

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. 11040-11040
Author(s):  
Udhayvir Singh Grewal ◽  
Jamie Doggett ◽  
Emil Lou ◽  
Allyson J. Ocean ◽  
Niraj Jaysukh Gusani ◽  
...  
Keyword(s):  
Machine Learning ◽  
Health Care ◽  
Pancreatic Cancer ◽  
Social Media ◽  
Analytical Tool ◽  
User Profiles ◽  
Future Studies ◽  
Treatment Research ◽  
The Impact ◽  
Treatment Table

11040 Background: Social media has an important role in addressing medical misinformation by connecting the global community of health care professional (HCP), cancer patients and advocates. We evaluated the content and dynamics of discussions around pancreatic cancer (PC) on Twitter to identify subtopics of greatest interest to these users. Methods: We used online analytical tool (CREATION Pinpoint) to quantify Twitter mentions (tweets and re-tweets) related to PC between 1/2018 to 12/2019. Keywords, hashtags, word combinations and phrases were used to query for PC mentions. HCP profiles were identified using machine learning and then human verified and remaining user profiles were classified as general public (GP). Data from conversations were analysed and stratified qualitatively (using e.g keywords/combinations/phrases) into 5 categories; 1) prevention (P), 2) survivorship (S), 3) treatment (T), 4) research (R), and 5) policy (Po). We analysed the impact of PC awareness month (PCAM) and celebrity PC diagnosis on the overall level of conversations. Results: Out of 1,258,028 mentions on PC, 313,668 unique mentions were classified into the 5 categories. We found that HCP discuss PC research more than the GP, while GP are more interested in treatment. PCAM did not increase mentions by HCP in any of 5 categories while GP mentions over 2 years, increased temporarily in all categories except prevention. HCP mentions did not increase with celebrity PC diagnosis. Alex Trebek’s diagnosis increased GP mentions on survivorship, while Ruth Ginsburg’s diagnosis increased conversations on treatment (Table). Conclusions: Twitter mentions between HCP and GP around PC are not aligned. The HCP conversation was mainly limited to research while GP were more interested in treatment. PCAM temporarily increased GP conversations around treatment, research, survivorship and policy but not prevention. Future studies should address which factors determine how celebrity diagnoses drive conversations. [Table: see text]

scholarly journals I Know Where You Are Coming From: On the Impact of Social Media Sources on AI Model Performance (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13971-13972
Author(s):  
Yang Qi ◽  
Farseev Aleksandr ◽  
Filchenkov Andrey
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Media ◽  
Social Network ◽  
Model Performance ◽  
User Profiling ◽  
Personalized Recommendation ◽  
Modal Data ◽  
Social Media Networks ◽  
The Impact

Nowadays, social networks play a crucial role in human everyday life and no longer purely associated with spare time spending. In fact, instant communication with friends and colleagues has become an essential component of our daily interaction giving a raise of multiple new social network types emergence. By participating in such networks, individuals generate a multitude of data points that describe their activities from different perspectives and, for example, can be further used for applications such as personalized recommendation or user profiling. However, the impact of the different social media networks on machine learning model performance has not been studied comprehensively yet. Particularly, the literature on modeling multi-modal data from multiple social networks is relatively sparse, which had inspired us to take a deeper dive into the topic in this preliminary study. Specifically, in this work, we will study the performance of different machine learning models when being learned on multi-modal data from different social networks. Our initial experimental results reveal that social network choice impacts the performance and the proper selection of data source is crucial.

scholarly journals INTERCAMBIO TRASFRONTERIZO DE SERVICIOS DE SALUD Y MEDICINAS EN LA REGIÓN DE TIJUANA Y SAN DIEGO

2010 ◽  
Vol 5 (10) ◽  
pp. 303
Author(s):  
José G. Vargas-Hernández
Keyword(s):  
Health Care ◽  
Health Services ◽  
Regional Development ◽  
San Diego ◽  
Negative Consequences ◽  
Review Of The Literature ◽  
Border Area ◽  
Future Studies ◽  
Documentary Analysis ◽  
The Impact

Este trabajo tiene por objetivo analizar el intercambio fronterizo en la región Tijuana-San Diego de los servicios de atención médica, cuidados de la salud y medicamentos. Aun con un gran número de investigaciones y estudios, todavía se tienen muchos cuestionamientos con respecto al impacto de este intercambio en el desarrollo regional. El método empleado es exploratorio, analítico documental y de revisión de la literatura existente. En este trabajo se delimita el mercado trasfronterizo del sur de California y la zona fronteriza de Tijuana, las motivaciones de los usuarios y compradores, las principales barreras, características y tipología. Se enuncian algunas de las áreas para futuras investigaciones y finalmente se formulan algunas propuestas que tienen implicaciones en las políticas públicas. Este estudio arroja luz sobre la posibilidad de elevar los ingresos provenientes del comercio de los servicios de salud, mejorar la satisfacción de los usuarios y consumidores y mitigar las consecuencias negativas asociadas con el diseño de políticas y de iniciativas en los ámbitos multilateral, binacional, regional.    ABSTRACTThe objective of this article is to analyze the border exchange in the Tijuana-San Diego region of medical services, health care and medicines. Despite the numerous research studies conducted, there are still many questions regarding the impact from this exchange on regional development. The exploratory method, documentary analysis and a review of the literature were utilized. This article is focused on the transboundary market of southern California and the Tijuana border area, the motivations of users and buyers, the main barriers, characteristics and typology. Some areas for future studies are specified, and lastly, some proposals with implications for public policies are formulated. This study sheds light on the possibilities of increasing income from commerce in health services, improving the satisfaction of users and consumers, and mitigating the negative consequences associated with the design of policies and initiatives at the multilateral, binational and regional levels.

scholarly journals 0386 Identification of Sleep Complaints Using Social Media: Effect of the Daylight Savings Time to Standard Time Transition

SLEEP ◽  
2020 ◽  
Vol 43 (Supplement_1) ◽  
pp. A148-A148
Author(s):  
O J Veatch ◽  
D R Mazzotti
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Random Forest ◽  
The United States ◽  
Natural Experiments ◽  
Media Effect ◽  
Sleep Complaints ◽  
Standard Time ◽  
The Impact ◽  
Circadian Patterns

Abstract Introduction Transitions to and from daylight savings time (DST) are natural experiments of circadian disruption and are associated with negative health consequences. Yet, the majority of the United States and several other countries still adopt these changes. Large observational studies focused on understanding the impact of DST transitions on sleep are difficult to conduct. Social media platforms, like Twitter, are powerful sources of human behavior data. We used machine learning to identify tweets reporting sleep complaints (TRSC) during the week of the standard time (ST)-DST transition. Next, we evaluated the circadian patterns of TRSC and compared their prevalence before and after the transition. Methods Using data publicly available via the Twitter API, we collected 500 tweets with evidence of sleep complaints, and manually annotated each tweet to validate true sleep complaints. Next, we calculated term frequency-inverse document frequency of each word in each tweet and trained a random forest to classify TRSC using a 3-fold cross-validation design. The trained model was then used to annotate a collection of tweets captured between Oct. 30, 2019-Nov. 6, 2019, overlapping with the DST-ST transition, which occurred on Nov. 3, 2019. Results Random forest demonstrated good performance in classifying TRSC (AUC[95%CI]=0.85[0.82-0.89]). This model was applied to 3,738,383 tweets collected around the DST-ST transition, and identified 11,044 TRSC. Posting of these tweets had a circadian pattern, with peak during nighttime. We found a higher frequency of TRSC after the DST-ST transition (0.33% vs. 0.27%, p<0.00001), corresponding to a ~20% increase in the odds of reporting sleep complaints (OR[95%CI]=1.21[1.16-1.25]). Conclusion Using machine learning and Twitter data, we identified tweets reporting sleep complaints, described their circadian patterns and demonstrated that the prevalence of these types of tweets is significantly increased after the transition from DST to ST. These results demonstrate the applicability of social media data mining for public health in sleep medicine. Support NIH (K01LM012870); AASM Foundation (194-SR-18)

scholarly journals A Complete VADER-Based Sentiment Analysis of Bitcoin (BTC) Tweets during the Era of COVID-19

2020 ◽  
Vol 4 (4) ◽  
pp. 33
Author(s):  
Toni Pano ◽  
Rasha Kashef
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Prediction Model ◽  
Sentiment Analysis ◽  
Significant Role ◽  
Prediction Models ◽  
Financial Sector ◽  
Research Gap ◽  
Text Preprocessing ◽  
The Impact

During the COVID-19 pandemic, many research studies have been conducted to examine the impact of the outbreak on the financial sector, especially on cryptocurrencies. Social media, such as Twitter, plays a significant role as a meaningful indicator in forecasting the Bitcoin (BTC) prices. However, there is a research gap in determining the optimal preprocessing strategy in BTC tweets to develop an accurate machine learning prediction model for bitcoin prices. This paper develops different text preprocessing strategies for correlating the sentiment scores of Twitter text with Bitcoin prices during the COVID-19 pandemic. We explore the effect of different preprocessing functions, features, and time lengths of data on the correlation results. Out of 13 strategies, we discover that splitting sentences, removing Twitter-specific tags, or their combination generally improve the correlation of sentiment scores and volume polarity scores with Bitcoin prices. The prices only correlate well with sentiment scores over shorter timespans. Selecting the optimum preprocessing strategy would prompt machine learning prediction models to achieve better accuracy as compared to the actual prices.

scholarly journals Sentiment Analysis of Impact of Technology on Employment from Text on Twitter

2020 ◽  
Vol 14 (07) ◽  
pp. 88
Author(s):  
Shahzad Qaiser ◽  
Nooraini Yusoff ◽  
Farzana Kabir Ahmad ◽  
Ramsha Ali
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Social Issues ◽  
Support Vector ◽  
Ripple Effect ◽  
Learning Classifier ◽  
The People ◽  
Impact Of Technology ◽  
Negative Sentiment ◽  
The Impact

Many different studies are in progress to analyze the content created by the users on social media due to its influence and social ripple effect. Various content created on social media has pieces of information and user’s sentiments about social issues. This study aims to analyze people’s sentiments about the impact of technology on employment and advancements in technologies and build a machine learning classifier to classify the sentiments. People are getting nervous, depressed and even doing suicides due to unemployment; hence, it is essential to explore this relatively new area of research. The study has two main objectives 1) to preprocess text collected from Twitter concerning the impact of technology on employment and analyze its sentiment, 2) to evaluate the performance of machine learning Naïve Bayes (NB) classifier on the text. To achieve this, a methodology is proposed that includes 1) data collection and preprocessing 2) analyze sentiment, 3) building machine learning classifier and 4) compare the performance of NB and support vector machine (SVM). NB and SVM achieved 87.18% and 82.05% accuracy respectively. The study found that 65% of the people hold negative sentiment regarding the impact of technology on employment and technological advancements; hence people must acquire new skills to minimize the effect of structural unemployment.

scholarly journals Evolution of corporate reputation during an evolving controversy

2019 ◽  
Vol 23 (1) ◽  
pp. 52-71 ◽  
Author(s):  
Siyoung Chung ◽  
Mark Chong ◽  
Jie Sheng Chua ◽  
Jin Cheon Na
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Sentiment Analysis ◽  
Corporate Reputation ◽  
Supervised Machine Learning ◽  
Future Research ◽  
Content Type ◽  
Twitter Users ◽  
Corporate Crisis ◽  
The Impact

PurposeThe purpose of this paper is to investigate the evolution of online sentiments toward a company (i.e. Chipotle) during a crisis, and the effects of corporate apology on those sentiments.Design/methodology/approachUsing a very large data set of tweets (i.e. over 2.6m) about Company A’s food poisoning case (2015–2016). This case was selected because it is widely known, drew attention from various stakeholders and had many dynamics (e.g. multiple outbreaks, and across different locations). This study employed a supervised machine learning approach. Its sentiment polarity classification and relevance classification consisted of five steps: sampling, labeling, tokenization, augmentation of semantic representation, and the training of supervised classifiers for relevance and sentiment prediction.FindingsThe findings show that: the overall sentiment of tweets specific to the crisis was neutral; promotions and marketing communication may not be effective in converting negative sentiments to positive sentiments; a corporate crisis drew public attention and sparked public discussion on social media; while corporate apologies had a positive effect on sentiments, the effect did not last long, as the apologies did not remove public concerns about food safety; and some Twitter users exerted a significant influence on online sentiments through their popular tweets, which were heavily retweeted among Twitter users.Research limitations/implicationsEven with multiple training sessions and the use of a voting procedure (i.e. when there was a discrepancy in the coding of a tweet), there were some tweets that could not be accurately coded for sentiment. Aspect-based sentiment analysis and deep learning algorithms can be used to address this limitation in future research. This analysis of the impact of Chipotle’s apologies on sentiment did not test for a direct relationship. Future research could use manual coding to include only specific responses to the corporate apology. There was a delay between the time social media users received the news and the time they responded to it. Time delay poses a challenge to the sentiment analysis of Twitter data, as it is difficult to interpret which peak corresponds with which incident/s. This study focused solely on Twitter, which is just one of several social media sites that had content about the crisis.Practical implicationsFirst, companies should use social media as official corporate news channels and frequently update them with any developments about the crisis, and use them proactively. Second, companies in crisis should refrain from marketing efforts. Instead, they should focus on resolving the issue at hand and not attempt to regain a favorable relationship with stakeholders right away. Third, companies can leverage video, images and humor, as well as individuals with large online social networks to increase the reach and diffusion of their messages.Originality/valueThis study is among the first to empirically investigate the dynamics of corporate reputation as it evolves during a crisis as well as the effects of corporate apology on online sentiments. It is also one of the few studies that employs sentiment analysis using a supervised machine learning method in the area of corporate reputation and communication management. In addition, it offers valuable insights to both researchers and practitioners who wish to utilize big data to understand the online perceptions and behaviors of stakeholders during a corporate crisis.

scholarly journals Machine learning application to the reduction of ambulatory care sensitive admissions (ACSA)

2019 ◽  
Vol 29 (Supplement_4) ◽  
Author(s):  
T Ngo ◽  
V Georgescu ◽  
C Gervet ◽  
A Laurent ◽  
T Libourel ◽  
...  
Keyword(s):  
Machine Learning ◽  
Primary Care ◽  
Health Care ◽  
Ambulatory Care ◽  
Support Vector ◽  
Care Services ◽  
Health Authorities ◽  
Primary Care Workforce ◽  
The Impact ◽  
Ambulatory Care Sensitive

Abstract Background Reducing Ambulatory Care Sensitive Admissions (ACSA) not only enhances patients’ quality of life but could also save substantial costs. ACSA are avoidable admissions for chronic conditions that are associated with socio-economic status, health status, utilization and readiness of primary care service as well as environmental factors. Undoubtedly, health authorities are highly interested in enhancing the health care services in order to reduce the number of ACSA. The objective is to identify the geographic areas where the primary care workforce should be increased in order to maximize the decrease in ACSA. Methods Using ambulatory care and inpatient claims data as well as contextual variables, we apply support vector machine regression (SVR) to select the geographic areas (fr. Bassins de vie - BVs) and the number of to-be-added primary care nurses that maximize the ACSA reduction. We also take into account the constraints related to budget and the equality of health care access. Particularly, there are three possible constraints: (1) the total number of nurses can be added in the whole region; (2) the maximum number of the nurses can be added at each area; (3) the maximum density of nurses (numbers of the nurses per 10,000 habitants) can be reached at each area. The results are visualized using spatial maps. Preliminary results In 2014, 27,000 ACSA occurred in the Occitanie, France region. For a specific set of constraints values, the model identified 16 BVs (out of 201) where the addition of 30 nurses could lead to the maximum ACSA reduction in number which is 17. Conclusions In the French Occitanie region, our SVR model was able to target a small number of geographic areas to maximize the impact of increased primary care workforce on ACSA. Our approach is applied to a single region, and it can be applied to other regions or extended at the national level as well as to other countries. Key messages A decision support tool to help health authorities in locating primary health care resources for the maximum reduction of ambulatory care sensitive admissions. An application of machine learning in primary care services.

Is it cost-effective to add erlotinib to gemcitabine in advanced pancreatic cancer?

2006 ◽  
Vol 24 (18_suppl) ◽  
pp. 6048-6048 ◽  
Author(s):  
S. S. Grubbs ◽  
P. A. Grusenmeyer ◽  
N. J. Petrelli ◽  
R. J. Gralla
Keyword(s):  
Health Care ◽  
Pancreatic Cancer ◽  
Cost Effectiveness ◽  
Incremental Cost ◽  
Health Care Costs ◽  
Advanced Pancreatic Cancer ◽  
Cost Effective ◽  
Significant Difference ◽  
The Impact ◽  
Care Costs

6048 Background: Single agent gemcitabine has been considered the standard of care in advanced pancreatic cancer since 1996. A recent 569 patient randomized trial comparing gemcitabine alone with gemcitabine + erlotinib as first line therapy found a small but statistically significant difference in survival (6.0 vs 6.4 months, respectively, p = .028). The impact on survival may be small, but with nearly 33,000 new cases of pancreatic cancer per year, the impact on health care costs with the use of the combined regimen may be large. Using the known survival data and costs, we analyzed the incremental cost-effectiveness of adding erlotinib. Methods: Costs for a six month course of gemcitabine were developed using Medicare reimbursement from the January, 2006 CMS Drug Payment Table and Physician Fee Schedule assuming no change in infusion reimbursement. Since erlotinib is not approved as a Medicare Part B drug, costs were developed from wholesale and retail sources. Drug dosing and schedules were based on the clinical trial protocol leading to approval. Incremental cost effectiveness of adding erlotinib was calculated. Results: Six month course of gemcitabine alone costs $23,493. The addition of erlotinib increases cost by $12,156 wholesale or $16,613 retail. Given an increase of 0.4 months in median survival over gemcitabine alone, the addition of erlotinib costs $364,680 per year of life gained (YLG) wholesale and $498,379/YLG retail. Sensitivity analyses were conducted assuming shorter therapy of 4 and 5 months. In order to be cost effective even at the $100,000/YLG level, six months of erlotinib would have to be reduced to 20% of the current retail cost (lowered to $18.52 per tablet.) Conclusions: Adding erlotinib to gemcitabine does not approach cost effectiveness at even the highest year per life gained parameters. Such impacts on health care costs, especially for very small gains, become more pressing as all health care costs continue to increase. [Table: see text] [Table: see text]

Introduction of #PancChat: A novel Twitter platform to inform and engage the pancreatic cancer community.

2018 ◽  
Vol 36 (4_suppl) ◽  
pp. 242-242
Author(s):  
Allyson J. Ocean ◽  
Niraj Jaysukh Gusani ◽  
Muhammad Shaalan Beg ◽  
Anirban Maitra ◽  
Julissa Viana ◽  
...  
Keyword(s):  
Health Care ◽  
Pancreatic Cancer ◽  
Social Media ◽  
Clinical Trials ◽  
Opportunity To Learn ◽  
Advocacy Organizations ◽  
Disease Research ◽  
Knowing That ◽  
Specific Community ◽  
Media Channels

242 Background: Twitter provides a platform for health care stakeholders to disseminate information about diseases to patients, caregivers, and doctors. Chats are especially effective because participants can interact directly with experts. Pancreatic cancer (PC) conversations on Twitter previously were sporadic and inconsistent. The authors report the creation of #PancChat, a first-of-its-kind Tweet Chat developed to provide relevant, credible, and timely information to the PC community. A collaboration between leading PC organizations, a pharmaceutical company, and an academic oncologist, PancChat is an example of successful outreach using an accessible communications tool. Methods: Launched in April 2016, the hour-long monthly chat is a live event publicized and promoted through multiple social media channels and major news outlets. It is moderated and focused around a pre-selected topic. The hashtag #PancChat is used to filter specific chatter into a single conversation. Participants include patients, caregivers, physicians, researchers, top ASCO social media influencers, AACR members, and advocacy organizations. Moderators and participants are drawn from 23 academic institutions. The PancChat team corresponds with participants and replies to tweets that are not addressed during the chat. Results: Since its inception, PancChat has had a total of 28 million impressions (the total number of times each tweet is seen) from 16 chats, averaging 1.75 million per chat. Popular topics include clinical trials (1.4 million), familial/hereditary PC (2.9 million), and early detection (2.2 million). The average engagement rate is 72% which measures how much people interact with a tweet by clicking or sharing links. From April 2016-August 2017 there were 8,502 tweets using #PancChat. Conclusions: Impression and engagement numbers show that this novel PancChat platform fulfills a need for the PC community. The narrow focus of each chat provides an opportunity to learn about the disease, research, and clinical trials. Participants return knowing that they will interact with PC experts. The popularity of PancChat among patients and doctors confirms the power of social media to reach a specific community.

Sign in / Sign up

Export Citation Format

Share Document