145 research outputs found
Unsupervised Model for Topic Viewpoint Discovery in Online Debates Leveraging Author Interactions
No full textOnline debate forums provide a valuable resource for textual discussions about controversial social and political issues. Discovering the viewpoints and their discourse or arguments from such resources is important for policy and decision makers. In order to detect the stance, most of the existing methods rely on expensively obtained human annotations and propose supervised solutions. In this work, we introduce a purely unsupervised Author Interaction Topic Viewpoint model (AITV) for viewpoint identification at the post and the discourse levels. The model favors "heterophily" over "homophily" when encoding the nature of the authors' interactions in online debates. It assumes that the difference in viewpoints breeds interactions, unlike similar studies based on social network analysis, which hypothesize that similar viewpoints encourage interactions. We evaluate the model's viewpoint identification and clustering accuracies at the author and post levels. Experiments are held on six corpora about four different controversial issues, extracted from two online debate forums. AITV's results show a better performance in terms of viewpoint identification at the post level than the state-of-the-art supervised methods in terms of stance prediction, even though it is unsupervised. It also outperforms a recently proposed topic model for viewpoint discovery in social networks and achieves close results to a weakly guided unsupervised method in terms of author level viewpoint identification. Our results highlight the importance of encoding "heterophily" for purely unsupervised viewpoint identification in the context of online debates. We also carry out a brief qualitative evaluation of the discourse modeling in terms of Topic-Viewpoint word clusters. AITV shows encouraging results suggesting an accurate discovery of the viewpoints and topics' discourses
Simply the Best:Minimalist System Trumps Complex Models in Author Profiling
No full textA simple linear SVM with word and character n-gram features and minimal parameter tuning can identify the gender and the language variety (for English, Spanish, Arabic and Portuguese) of Twitter users with very high accuracy. All our attempts at improving performance by including more data, smarter features, and employing more complex architectures plainly fail. In addition, we experiment with joint and multitask modelling, but find that they are clearly outperformed by single task models. Eventually, our simplest model was submitted to the PAN 2017 shared task on author profiling, obtaining an average accuracy of 0.86 on the test set, with performance on sub-tasks ranging from 0.68 to 0.98. These were the best results achieved at the competition overall.To allow lay people to easily use and see the value of machine learning for author profiling, we also built a web application on top our models
Simply the Best:Minimalist System Trumps Complex Models in Author Profiling
No full textA simple linear SVM with word and character n-gram features and minimal parameter tuning can identify the gender and the language variety (for English, Spanish, Arabic and Portuguese) of Twitter users with very high accuracy. All our attempts at improving performance by including more data, smarter features, and employing more complex architectures plainly fail. In addition, we experiment with joint and multitask modelling, but find that they are clearly outperformed by single task models. Eventually, our simplest model was submitted to the PAN 2017 shared task on author profiling, obtaining an average accuracy of 0.86 on the test set, with performance on sub-tasks ranging from 0.68 to 0.98. These were the best results achieved at the competition overall.To allow lay people to easily use and see the value of machine learning for author profiling, we also built a web application on top our models
Prevalence and Factors Associated with Group A Rotavirus Infection Among Children with Acute Diarrhea in Mwanza, Tanzania.
No full textRotavirus infections frequently cause acute gastroenteritis in humans and are the most important cause of severe dehydrating diarrhea in young children in both developed and developing countries. This was a prospective cross-sectional, hospital-based study on 300 children ≤ 5 years with acute watery diarrhea who attended Bugando Medical Centre (BMC) and Nyamagana District hospital between May and November 2009. Stool specimens were tested for rotavirus infection using latex agglutination test. Data were cleaned and analyzed using SPSS 11.0. Of 300 children with acute watery diarrhea, 136 (45.3%) were female and the mean age was 12.63 months (SD = 10.4). Sixty-two (20.7%) children were found to have rotavirus infection. Of children with severe malnutrition three (37.5%) were infected with rotavirus. Fifty-two (84%) of children with rotavirus infection were below two years of age. Severe dehydration was present in 48 (16%) children of whom 12 (25%) were infected with rotavirus compared to 18 (16.6%) of 109 children with no dehydration. Living next door to a child with diarrhea was highly associated with rotavirus infection (43% versus 19%; p = 0.036). The mean hospital stay among children with rotavirus infection was 3.66 days versus 2.5 days for those without rotavirus (p = 0.005). Rotavirus infection is prevalent in Mwanza region and contributes to prolonged hospital stay. Proper education on hygiene to control diarrheal diseases among children should be emphasized. Extensive studies to determine the serotypes of rotavirus are warranted in the region before rotavirus vaccine is introduced
PhAITV: A Phrase Author Interaction Topic Viewpoint Model for the Summarization of Reasons Expressed by Polarized Stances
No full textThis work tackles the problem of unsupervised modeling and extraction of the main contrastive sentential reasons conveyed by divergent viewpoints in text documents. It proposes a pipeline framework that is centered around the detection and clustering of phrases, assimilated to argument facets using a novel Phrase Author Interaction Topic-Viewpoint (PhAITV) model. The evaluation is conducted on all the components of the framework. It is mainly based on the informativeness, the relevance and the clustering accuracy of extracted reasons. The framework shows a significant improvement over several configurations and state-of-the-art methods in contrastive summarization on online debate datasets
Exploration of contrastive learning strategies toward more robust stance detection systems
No full textStance Detection, in general, is the task of identifying the author’s position on controversial topics. In Natural Language Processing, Stance Detection extracts the
author’s attitude from the text written toward an issue to determine whether the author supports the issue or is against the issue. The studies analyzing public opinion
on social media, especially in relation to political and social concerns, heavily rely on
Stance Detection. The linguistics of social media texts and articles are often unstructured. Hence, the Stance Detection systems needed to be robust when identifying
the position or stance of an author on a topic. This thesis seeks to contribute to the
ongoing research on Stance Detection. This research proposes a Contrastive Learning approach to achieve the goal of learning sentence representations leading to more
robust Stance Detection systems. Further, this thesis explores the possibility of extending the proposed methodology to detect stances from unlabeled or unannotated
data. The stance of an author towards a topic can be implicit (through reasoning)
or explicit; The proposed method learns the sentence representations in a contrastive
fashion to learn the sentence-level meaning. The Contrastive Learning of sentence
representations results in bringing similar examples in the Sentence Representation
space belonging to the same stance close to each other, whereas the dissimilar examples are far apart. The proposed method also accommodates the token-level meaning
by combining the Masked Language Modeling objective (similar to BERT pretraining)
with the Contrastive Learning objective. [...
Guts of healthy humans, livestock, and pets harbor critical-priority and high-risk Escherichia coli clones
No full textOBJECTIVES: In May 2024, the World Health Organization classified carbapenem (CARB)- and third-generation cephalosporin (3GC) resistance (R) in Escherichia coli as a critical priority, whereas colistin (COL) is a "last resort" antibiotic for their treatment. This meta-analysis evaluated the pooled prevalence, high-risk lineages, genetic relatedness, and mechanisms of CARBR, COLR, and 3GCR in E. coli from healthy humans and animals. METHODS: We conducted a systematic review and meta-analyses following the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) criteria on all eligible studies that reported the analysis of E. coli, and antimicrobial susceptibility to CARB, COL and 3GC in E. coli from gut samples of clinically healthy humans, livestock, and pets from June 2014 to June 2024. Random-effect models and conserved signature indels phylogeny 1.4 were used to determine pooled prevalence rates (PPs) and the relatedness of publicly available E. coli genomes, respectively. RESULTS: Of the 5,034 identified articles, 64 studies were deemed eligible. The overall PPs of 3GCR, CARBR, and COLR E. coli were 22.5% (95% confidence interval [CI], 17.5 to 28.3), 2.2% (95% CI, 1.0 to 4.7), and 15.5% (95% CI, 10.8 to 21.8), respectively. The PPs of 3GCR-, COLR- and CARBR E. coli significantly varied by hosts, continent, and year of studies (pE. coli lineages were found, including 13 high-risk E. coli sequence types (STs), within which ST10 predominated. Phylogenomic analyses produced 4 clusters of related CARBR- and COLR E. coli strains (blaOXA-181 from humans in Lebanon, ST617-mcr-1 from pigs in China, ST46-mcr-1 from poultry in Tanzania, and ST1720-mcr-1 from goats in France. CONCLUSIONS: COLR and 3GCR are more frequent than CARBR in gut E. coli. These 10-year epidemiological data highlight the persistence and transmission of critical priority and high-risk E. coli strains in healthy humans and animals, raising significant One Health concerns
Lyapunov-Based Model Predictive Control for Stable Operation of a 9-Level Crossover Switches Cell Inverter in Grid Connection Mode
No full textThis study proposes the application of a Lyapunov-based Model Predictive Control (L-MPC) approach to a 9-level Crossover Switches Cell (CSC9) converter operating in grid connection mode. The proposed method utilizes the structure of the classical finite-control-set MPC (FCS-MPC) technique while integrating a cost function that requires no tuning. By deriving the cost function based on Lyapunov theory, the system stability is ensured. Notably, the suggested approach offers several advantages over traditional MPC controllers. Firstly, it eliminates the need for gain tuning, thereby simplifying the implementation process. Secondly, the proposed controller prioritizes stability as a key design aspect. The presented simulation results prove that the proposed controller effectively regulates the voltage of the DC capacitor around its desired value and feed a smooth sinusoidal current to the grid with low total harmonic distortion (THD) while operating at a unity power factor.Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.DC systems, Energy conversion & Storag
Unsupervised Mining and Summarization of Polarized Contentious Issues from Online Text
No full textThis thesis seeks to contribute to the ongoing research on opinion mining. The contributions are related to the development of newly conceived models for discovery of the viewpoints, and the reasons supporting them, from various polarized contentious texts found in surveys' responses, debate websites, and editorials.
This research proposes a purely unsupervised approach without the need for annotated large data or any type of external guidance. It deals only with raw documents consisting of real and unstructured social media text. In this respect, we first suggest a novel Joint Topic Viewpoint (JTV) Bayesian probabilistic model and a modified clustering algorithm to automatically generate idiosyncratic and informative patterns of associated terms denoting a vocabulary for a specific reason. Terms are clustered according to the hidden topics that they discuss and the embedded viewpoint that they voice. The coherence of the distinct reasons' lexicons is shown to be of a high quality. The performance of JTV in clustering exceeds that of state-of-the-art and baseline methods. This out-performance is reiterated for six datasets associated with three different types of contentious documents.
Moreover, we formulate a purely unsupervised Author Interaction Topic Viewpoint model (AITV) at the post and the discourse levels. AITV integrates not just the content of the posts, like JTV, but also the reply information about the authors' interactions. The model assumes heterophily when encoding the nature of the authors’ interactions. Heterophily suggests that the difference in viewpoints breeds interactions. We evaluate the model’s viewpoint identification and clustering accuracies at the author and post levels. Experiments are run on six corpora about four different controversial issues, extracted from two online debate forums. AITV’s results show a higher performance in terms of viewpoint identification at the post-level than the state-of-the-art supervised methods in terms of stance prediction. It also outperforms a recently proposed topic model for viewpoint discovery in social networks and achieves close results to a weakly guided unsupervised method in terms of author-level viewpoint identification. Our results highlight the importance of encoding heterophily for purely unsupervised viewpoint identification in the context of online debates.
Finally, we design a generic pipeline framework to effectively produce a contrastive textual summary of the main viewpoints given by each of the opposed sides in the form of a fine-grained digest table. The digest table is a realization of the process of automatic extraction and display of the major distinct reasons put forward in the text, according to their topics or facets of argumentation and to their divergent viewpoints. The modular pipeline framework contains a phrase mining, a Topic Viewpoint, and reasons extraction modules. A Phrase Author Interaction Topic Viewpoint model PhAITV is suggested as pipeline component, extending AITV, which jointly processes phrases of different length, instead of just unigrams, and leverages the interaction of authors in online debates. An extensive evaluation of the final produced table is conducted on text about issues extracted from different forums. The evaluation procedure is based on three measures: the informativeness of the digest table as a summary, the relevance of extracted sentences as reasons and the accuracy of their viewpoint clustering. The results on different issues show that our pipeline improves significantly over two state-of-the-art methods and several baselines when measured in terms of documents' summarization, reasons' retrieval, and viewpoint clustering
What is the impact of social well-being factors on happiness?
No full textPurpose – The purpose of this study is to examine the effect of social support, healthy life expectancy, freedom to make life choices, generosity, corruption perception, real gross domestic product per capita and the Gini index on happiness. Design/methodology/approach – In this study, the sample consists of 137 countries observed over the period 2017–2019. A multidimensional approach is used consisting of a principal component analysis and an econometric linear regression model. Findings – The findings indicate that perception, taking care of other people, corruption perception, freedom to make life choices and healthy life expectancy are the most determining factors of social well-being. Practical implications – Well-being benefits countries by improving living standards. Indeed, taking care of other people, corruption perception, freedom to make life choices and healthy life expectancy directly and positively correlate with social well-being. Originality/value – This study contributes to the previous literature in three ways. First, this paper provides fresh and recent data on social well-being. Second, the author introduced a multidimensional approach using a principal component analysis of the different social well-being factors to detect correlation between these indicators and to determine homogeneous clusters. Third, through these indicators, a country's leaders can formulate policies to enhance social well-being because it is closely linked to the improvement of the standard of living, good governance and therefore an increase in GDP
- …
