Infant food users' perceptions of safety: A web-based analysis approach

This paper aims to explore consumer beliefs about health hazards in infant foods by analyzing data gathered from the web, focusing on forums for parents in the UK. After selecting a subset of posts and classifying them by topic, according to the food product discussed and the health hazard discussed, two types of analyses were performed. Pearson correlation of term-occurrences highlighted what hazard-product pairs are most prevalent. Ordinary Least Squares (OLS) regression performed on sentiment measures generated from the texts provided significant results indicating positive or negative sentiment, objective or subjective language, and confident or unconfident modality associated with different food products and health hazards. The results allow comparison between perceptions obtained in different countries in Europe and may lead to recommendations concerning information and communication priorities.

Deep Learning in the Detection of Disinformation about COVID-19 in Online Space

This article focuses on the problem of detecting disinformation about COVID-19 in online discussions. As the Internet expands, so does the amount of content on it. In addition to content based on facts, a large amount of content is being manipulated, which negatively affects the whole society. This effect is currently compounded by the ongoing COVID-19 pandemic, which caused people to spend even more time online and to get more invested in this fake content. This work brings a brief overview of how toxic information looks like, how it is spread, and how to potentially prevent its dissemination by early recognition of disinformation using deep learning. We investigated the overall suitability of deep learning in solving problem of detection of disinformation in conversational content. We also provided a comparison of architecture based on convolutional and recurrent principles. We have trained three detection models based on three architectures using CNN (convolutional neural networks), LSTM (long short-term memory), and their combination. We have achieved the best results using LSTM (F1 = 0.8741, Accuracy = 0.8628). But the results of all three architectures were comparable, for example the CNN+LSTM architecture achieved F1 = 0.8672 and Accuracy = 0.852. The paper offers finding that introducing a convolutional component does not bring significant improvement. In comparison with our previous works, we noted that from all forms of antisocial posts, disinformation is the most difficult to recognize, since disinformation has no unique language, such as hate speech, toxic posts etc.

Machine Learning and Lexicon Approach to Texts Processing in the Detection of Degrees of Toxicity in Online Discussions

This article focuses on the problem of detecting toxicity in online discussions. Toxicity is currently a serious problem when people are largely influenced by opinions on social networks. We offer a solution based on classification models using machine learning methods to classify short texts on social networks into multiple degrees of toxicity. The classification models used both classic methods of machine learning, such as naïve Bayes and SVM (support vector machine) as well ensemble methods, such as bagging and RF (random forest). The models were created using text data, which we extracted from social networks in the Slovak language. The labelling of our dataset of short texts into multiple classes-the degrees of toxicity-was provided automatically by our method based on the lexicon approach to texts processing. This lexicon method required creating a dictionary of toxic words in the Slovak language, which is another contribution of the work. Finally, an application was created based on the learned machine learning models, which can be used to detect the degree of toxicity of new social network comments as well as for experimentation with various machine learning methods. We achieved the best results using an SVM-average value of accuracy = 0.89 and F1 = 0.79. This model also outperformed the ensemble learning by the RF and Bagging methods; however, the ensemble learning methods achieved better results than the naïve Bayes method.

Comparison of Machine Learning and Sentiment Analysis in Detection of Suspicious Online Reviewers on Different Type of Data

The article focuses on solving an important problem of detecting suspicious reviewers in online discussions on social networks. We have concentrated on a special type of suspicious authors, on trolls. We have used methods of machine learning for generation of detection models to discriminate a troll reviewer from a common reviewer, but also methods of sentiment analysis to recognize the sentiment typical for troll’s comments. The sentiment analysis can be provided also using machine learning or lexicon-based approach. We have used lexicon-based sentiment analysis for its better ability to detect a dictionary typical for troll authors. We have achieved Accuracy = 0.95 and F1 = 0.80 using sentiment analysis. The best results using machine learning methods were achieved by support vector machine, Accuracy = 0.986 and F1 = 0.988, using a dataset with the set of all selected attributes. We can conclude that detection model based on machine learning is more successful than lexicon-based sentiment analysis, but the difference in accuracy is not so large as in F1 measure.

Detecting Misleading Information on COVID-19

This article addresses the problem of detecting misleading information related to COVID-19. We propose a misleading-information detection model that relies on the World Health Organization, UNICEF, and the United Nations as sources of information, as well as epidemiological material collected from a range of fact-checking websites. Obtaining data from reliable sources should assure their validity. We use this collected ground-truth data to build a detection system that uses machine learning to identify misleading information. Ten machine learning algorithms, with seven feature extraction techniques, are used to construct a voting ensemble machine learning classifier. We perform 5-fold cross-validation to check the validity of the collected data and report the evaluation of twelve performance metrics. The evaluation results indicate the quality and validity of the collected ground-truth data and their effectiveness in constructing models to detect misleading information.

Retrieving the Vital Status of Patients with Cancer Using Online Obituaries

The aim of this study was to develop a methodology to link mortality data from Internet sources with administrative data from electronic health records and to assess the performance of different record linkage methods. We extracted the electronic health records of all adult patients hospitalized at Rennes comprehensive cancer center between January 1, 2010 and December 31, 2015 and separated them in two groups (training and test set). We also extracted all available online obituaries from the most exhaustive French funeral home website using web scraping techniques. We used and evaluated three different algorithms (deterministic, approximate deterministic and probabilistic) to link the patients' records with online obituaries. We optimized the algorithms using the training set and then evaluated them in the test set. The overall precision was between 98 and 100%. The three classification algorithms performed better for men than women. The probabilistic classification decreased the number of manual reviews, but slightly increased the number of false negatives. To address the problem of long delays in the publication or sharing of mortality data, online obituary data could be considered for real-time surveillance of mortality in patients with cancer because they are easily available and time-efficient.

The utility of web mining for epidemiological research: studying the association between parity and cancer risk

BACKGROUND

The World Wide Web has emerged as a powerful data source for epidemiological studies related to infectious disease surveillance. However, its potential for cancer-related epidemiological discoveries is largely unexplored.

METHODS

Using advanced web crawling and tailored information extraction procedures, the authors automatically collected and analyzed the text content of 79 394 online obituary articles published between 1998 and 2014. The collected data included 51 911 cancer (27 330 breast; 9470 lung; 6496 pancreatic; 6342 ovarian; 2273 colon) and 27 483 non-cancer cases. With the derived information, the authors replicated a case-control study design to investigate the association between parity (i.e., childbearing) and cancer risk. Age-adjusted odds ratios (ORs) with 95% confidence intervals (CIs) were calculated for each cancer type and compared to those reported in large-scale epidemiological studies.

RESULTS

Parity was found to be associated with a significantly reduced risk of breast cancer (OR = 0.78, 95% CI, 0.75-0.82), pancreatic cancer (OR = 0.78, 95% CI, 0.72-0.83), colon cancer (OR = 0.67, 95% CI, 0.60-0.74), and ovarian cancer (OR = 0.58, 95% CI, 0.54-0.62). Marginal association was found for lung cancer risk (OR = 0.87, 95% CI, 0.81-0.92). The linear trend between increased parity and reduced cancer risk was dramatically more pronounced for breast and ovarian cancer than the other cancers included in the analysis.

CONCLUSION

This large web-mining study on parity and cancer risk produced findings very similar to those reported with traditional observational studies. It may be used as a promising strategy to generate study hypotheses for guiding and prioritizing future epidemiological studies.

Methods of knowledge discovery in tweets

1) to describe web mining methods for knowledge discovery in Tweets, and 2) to illustrate application of the methods using the topic of physical activity. Methods described include: 1) structure mining to discover structures (macro-, meso-, and micro-level) of Tweet networks using social network analysis, and 2) content mining to discover Tweet contents using n-gram based text analysis and sentiment analysis. Specific web mining tools for each step of the web mining process (e.g., NodeXL, ORA, Pajek, Weka) are detailed. Our novel application of web mining methods was useful in understanding multiple dimensions of physical activity. The methods that we applied may be useful to others wishing to mine social media for health-related purposes.

An intelligent tool for activity data collection

Activity recognition systems using simple and ubiquitous sensors require a large variety of real-world sensor data for not only evaluating their performance but also training the systems for better functioning. However, a tremendous amount of effort is required to setup an environment for collecting such data. For example, expertise and resources are needed to design and install the sensors, controllers, network components, and middleware just to perform basic data collections. It is therefore desirable to have a data collection method that is inexpensive, flexible, user-friendly, and capable of providing large and diverse activity datasets. In this paper, we propose an intelligent activity data collection tool which has the ability to provide such datasets inexpensively without physically deploying the testbeds. It can be used as an inexpensive and alternative technique to collect human activity data. The tool provides a set of web interfaces to create a web-based activity data collection environment. It also provides a web-based experience sampling tool to take the user’s activity input. The tool generates an activity log using its activity knowledge and the user-given inputs. The activity knowledge is mined from the web. We have performed two experiments to validate the tool’s performance in producing reliable datasets.