23 research outputs found
A study of the stylistic markers of the language of cartoons in Nigeria
No full textThis paper discusses the stylistic characteristics of the language of cartoons in some Nigerian newspapers. The analysis focuses on printing styles, stylistic registers, and textual features. The author concludes that the informal style (exemplified by the occurrence of Pidgin English, colloquial forms, loan blends, ellipsis, and telegraphic sentences) characterizes the language of the cartoons. Thus, cartoonists use language as an artistic medium in which various options of language are explored for effective communication
Regularized Deep Neural Network for Post-Authorship Attribution
No full textA thesis submitted to the Faculty of Science, in fulfillment of the requirements for the degree of Doctor of Philosophy in Computer Science, School of Science, University of the Witwatersrand, Johannesburg, 2024Post-authorship attribution is the computational process of determining the legitimate author of an online text snippet, such as an email, blog, forum post, or chat log, by employing stylometric features. The process consists of analysing various linguistic and writing patterns, such as vocabulary, sentence structure, punctuation usage, and even the use of specific words or phrases. By comparing these features to a known set of writing pieces from potential authors, investigators can make educated hypotheses about the true authorship of a text snippet. Additionally, post-authorship attribution has applications in fields like forensic linguistics and cybersecurity, where determining the source of a text can be crucial for investigations or identifying potential threats. Furthermore, in a verification procedure to proactively uncover misogynistic, misandrist, xenophobic, and abusive posts on the internet or social networks, finding a suitable text representation to adequately symbolise and capture an author’s distinctive writing from a computational linguistics perspective is typically known as a stylometric analysis. Additionally, most of the posts on social media or online are generally rife with ambiguous terminologies that could potentially compromise and influence the precision of the early proposed authorship attribution model. The majority of extracted stylistic elements in words are idioms, onomatopoeias, homophones, phonemes, synonyms, acronyms, anaphora, and polysemy, which are fundamentally difficult to interpret by most existing natural language processing (NLP) systems. These difficulties make it difficult to correctly identify the true author of a given text. Therefore, further advancements in NLP systems are necessary to effectively handle these complex linguistic elements and improve the accuracy of authorship attribution models.
In this thesis, we introduce a regularised deep neural network (RDNN) model to solve the challenges that come with figuring out who wrote what after the fact. The proposed method utilises a convolutional neural network, a bidirectional long short-term memory encoder, and a distributed highway network to effectively address the post-authorship attribution problem. The neural network was utilised to generate lexical stylometric features, which were then fed into the bidirectional encoder to produce a syntactic feature vector representation. The feature vector was then fed into the distributed high-speed networks for regularisation to reduce network generalisation errors. The regularised feature vector was then given to the bidirectional decoder to learn the author’s writing style. The feature classification layer is made up of a fully connected network and a SoftMax function for prediction. The RDNN method outperformed the existing state-of-the-art methods in terms of accuracy, precision, and recall on the majority of the benchmark datasets. These results highlight the potential of the proposed method to significantly improve classification performance in various domains. Again, the introduction of an interactive system to visualise the performance of the proposed method would further enhance its usability and effectiveness in quantifying the contribution of the author’s writing characteristics in both online text snippets and literary documents. It is useful in processing the evidence that is needed to support claims or draw conclusions about the author’s writing style or intent during the pre-trial investigation by the law enforcement agent in the court of law. The incorporation of this method into the pretrial stage greatly
strengthens the credibility and validity of the findings presented in court and has the potential to revolutionise the field of authorship attribution and enhance the accuracy of forensic investigations. Furthermore, it ensures a fair and just legal process for all parties involved by providing concrete evidence to support or challenge claims.
We are also aware of the limitations of the proposed methods and recognise the need for additional research to overcome these constraints and improve the overall reliability and applicability of post-authorship attribution of online text snippets and literary documents for forensic investigations. Even though the proposed methods have revealed some unusual differences in author writing style, such as how influential writers, regular people, and suspected authors use language, the evidence from the results with the features extracted from the texts has shown promise for identifying authorship patterns and aiding in forensic analyses. However, much work remains to be done to validate the methodologies’ usefulness and dependability as effective authorship attribution procedures. Further research is needed to determine the extent to which external factors, such as the context in which the text was written or the author’s emotional state, may impact the identified authorship patterns. Additionally, it is crucial to establish a comprehensive dataset that includes a diverse range of authors and writing styles to ensure the generalizability of the findings and enhance the reliability of forensic analyses.
Furthermore, the dataset used in this thesis does not include a diverse variety of authors and writing styles, such as impostors attempting to impersonate another author, which limits the generalizability of the conclusions and undermines the credibility of forensic analysis. More studies can be conducted to broaden the proposed strategy for detecting and distinguishing impostors’ writing styles from those of authentic authors when committing crimes on both online and literary documents. It is conceivable for numerous criminals to collaborate to perpetrate a crime, which could aid in improving the proposed methods for detecting the
existence of multiple impostors or the contribution of each criminal writing style based on the person or individual they are attempting to mimic. The likelihood of numerous offenders working together complicates the investigation and necessitates advanced procedures for identifying their individual contributions, as well as both authentic and manufactured impostor contents within the text. This is especially difficult on social media, where fake accounts and anonymous profiles can make it difficult to determine the true identity of those involved, which can come from a variety of sources, including text, WhatsApps, chat images, videos, and
so on, and can lead to the spread of misinformation and manipulation. As a result, promoting a hybrid approach that goes beyond text as evidence could help address some of the concerns raised above. For example, integrating audio and visual data may provide a more complete perspective of the scenario. As a result, such an approach exacerbates the restrictions indicated in the distribution of data and may necessitate more storage and analytical resources. However, it can also lead to a more accurate and nuanced analysis of the situationMM202
Making a case for an interdisciplinary approach to water education towards sustainable development
No full textTraditional engineering education has focused on design principles and the integrity of products. It includes the designs for water supply and sanitation systems, water resources management, hydraulic structures, to name a few. However, this approach has led to a gap in design and implementation, leading to challenges in product uptake and sustainability. Water is central to several Sustainable Development Goals (SDGs), creating a web between the technical, environmental, social, financial, policy, and governance subsectors. Water engineers are critical to attaining the SDG goals; therefore, they must be trained to acquire the skills required for the task. For example, the WASH humanitarian sector has reiterated that the lack of the right expertise has been a bane to the delivery of interventions. Sustainable water projects must incorporate techno-centric, eco-centric, and Socio-centric concerns. A redirection of the water syllabus to include all the necessary aspects is the step towards transferring and acquiring the required skills. Content review is critical when water education sits within a civil engineering program. This paper presents calls for interdisciplinary engineering education from literature. It highlights the benefits of interdisciplinary water engineering education. The paper also provides approaches taken by the author to design and deliver interdisciplinary water modules and feedback from the students on each of the approaches. Overall, advocates for educators, universities, and training institutes to produce graduates who understand water engineers' dependence on other sectors for successful and more-sustainable solutions for society
It's Good to Be the King
No full textEpidemiological and animal studies often find that higher social status is associated with better physical health outcomes, but these findings are by design correlational and lack mediational explanations. In two studies, we examine neurobiological reactivity to test the hypothesis that higher social status leads to salutary short-term psychological, physiological, and behavioral responses. In Study 1, we measured police officers' subjective social status and had them engage in a stressful task during which we measured cardiovascular and neuroendocrine reactivity. In Study 2, we manipulated social status and examined physiological reactivity and performance outcomes to explore links among status, performance, and physiological reactivity. Results indicated that higher social status (whether measured or manipulated) was associated with approach-oriented physiology (Studies 1 and 2) and better performance (Study 2) relative to lower status. These findings point to acute reactivity as one possible causal mechanism to better physical health among those higher in social status. © The Author(s) 2013
Post-authorship attribution using regularized deep neural network
No full textPost-authorship attribution is a scientific process of using stylometric features to identify
the genuine writer of an online text snippet such as an email, blog, forum post, or chat log. It has
useful applications in manifold domains, for instance, in a verification process to proactively detect
misogynistic, misandrist, xenophobic, and abusive posts on the internet or social networks. The
process assumes that texts can be characterized by sequences of words that agglutinate the functional
and content lyrics of a writer. However, defining an appropriate characterization of text to capture the
unique writing style of an author is a complex endeavor in the discipline of computational linguistics.
Moreover, posts are typically short texts with obfuscating vocabularies that might impact the accuracy
of authorship attribution. The vocabularies include idioms, onomatopoeias, homophones, phonemes,
synonyms, acronyms, anaphora, and polysemy. The method of the regularized deep neural network
(RDNN) is introduced in this paper to circumvent the intrinsic challenges of post-authorship attribution.
It is based on a convolutional neural network, bidirectional long short-term memory encoder,
and distributed highway network. The neural network was used to extract lexical stylometric features
that are fed into the bidirectional encoder to extract a syntactic feature-vector representation. The
feature vector was then supplied as input to the distributed high networks for regularization to
minimize the network-generalization error. The regularized feature vector was ultimately passed
to the bidirectional decoder to learn the writing style of an author. The feature-classification layer
consists of a fully connected network and a SoftMax function to make the prediction. The RDNN
method was tested against thirteen state-of-the-art methods using four benchmark experimental
datasets to validate its performance. Experimental results have demonstrated the effectiveness of the
method when compared to the existing state-of-the-art methods on three datasets while producing
comparable results on one dataset.The Department of Science and Technology (DST) and the Council for Scientific and Industrial Research (CSIR).https://www.mdpi.com/journal/applsciam2023Computer Scienc
Food insecurity in people living with obesity: improving sustainable and healthier food choices in the retail food environment: the FIO Food project.
No full textAt both UK and global level, dietary consumption patterns need to change to address environmental, health and inequality challenges. Despite considerable policy interventions, the prevalence of overweight and obesity in the United Kingdom has continued to rise, with obesity now a leading cause of mortality and morbidity. Obesity prevalence is greater among those on lower incomes and the current UK food system, including government policy, does not effectively address this. Current behavioural approaches, without the support of structural changes in the system, may even widen the inequalities gap. Hence, using behavioural insights from those living with obesity and food insecurity, the project will explore potential avenues that can be applied in the food system to promote healthier choices in the food retail environment. The National Food Strategy report recommends that the UK food system should ensure "safe, healthy, affordable food; regardless of where people live or how much they earn". However, the association between food insecurity and the development of obesity is not well understood in relation to purchasing behaviours in the UK retail food environment, nor is the potential effectiveness of interventions that seek to prevent and reduce the impact of diet-induced health harms. The FIO Food (Food insecurity in people living with obesity – improving sustainable and healthier food choices in the retail food environment) project provides a novel and multi-disciplinary collaborative approach with co-development at its heart to address these challenges. Using four interlinked work packages, the FIO Food project will combine our knowledge of large-scale population data with an understanding of lived experiences of food shopping for people living with obesity and food insecurity, to develop solutions to support more sustainable and healthier food choices in the UK retail food environment
Post-Authorship Attribution Using Regularized Deep Neural Network
No full textPost-authorship attribution is a scientific process of using stylometric features to identify the genuine writer of an online text snippet such as an email, blog, forum post, or chat log. It has useful applications in manifold domains, for instance, in a verification process to proactively detect misogynistic, misandrist, xenophobic, and abusive posts on the internet or social networks. The process assumes that texts can be characterized by sequences of words that agglutinate the functional and content lyrics of a writer. However, defining an appropriate characterization of text to capture the unique writing style of an author is a complex endeavor in the discipline of computational linguistics. Moreover, posts are typically short texts with obfuscating vocabularies that might impact the accuracy of authorship attribution. The vocabularies include idioms, onomatopoeias, homophones, phonemes, synonyms, acronyms, anaphora, and polysemy. The method of the regularized deep neural network (RDNN) is introduced in this paper to circumvent the intrinsic challenges of post-authorship attribution. It is based on a convolutional neural network, bidirectional long short-term memory encoder, and distributed highway network. The neural network was used to extract lexical stylometric features that are fed into the bidirectional encoder to extract a syntactic feature-vector representation. The feature vector was then supplied as input to the distributed high networks for regularization to minimize the network-generalization error. The regularized feature vector was ultimately passed to the bidirectional decoder to learn the writing style of an author. The feature-classification layer consists of a fully connected network and a SoftMax function to make the prediction. The RDNN method was tested against thirteen state-of-the-art methods using four benchmark experimental datasets to validate its performance. Experimental results have demonstrated the effectiveness of the method when compared to the existing state-of-the-art methods on three datasets while producing comparable results on one dataset
Consistency Over Flattery
No full textNegative social feedback is often a source of distress. However, self-verification theory provides the counterintuitive explanation that negative feedback leads to less distress when it is consistent with chronic self-views. Drawing from this work, the present study examined the impact of receiving self-verifying feedback on outcomes largely neglected in prior research: implicit responses (i.e., physiological reactivity, facial expressions) that are difficult to consciously regulate and downstream behavioral outcomes. In two experiments, participants received either positive or negative feedback from interviewers during a speech task. Regardless of self-views, positive compared to negative feedback elicited lower self-reported negative affect. Implicit responses to negative feedback, however, depended on chronic self-views with more negative self-views associated with lower blood pressure reactivity, lower facial negativity, and enhanced creativity. These findings point at the role self-verification may play in long-term coping and stress regulation. © The Author(s) 2013
Integrating Bidirectional Long Short-Term Memory with Subword Embedding for Authorship Attribution
No full textThe problem of unveiling the author of a given text document from multiple
candidate authors is called authorship attribution. Manifold word-based
stylistic markers have been successfully used in deep learning methods to deal
with the intrinsic problem of authorship attribution. Unfortunately, the
performance of word-based authorship attribution systems is limited by the
vocabulary of the training corpus. Literature has recommended character-based
stylistic markers as an alternative to overcome the hidden word problem.
However, character-based methods often fail to capture the sequential
relationship of words in texts which is a chasm for further improvement. The
question addressed in this paper is whether it is possible to address the
ambiguity of hidden words in text documents while preserving the sequential
context of words. Consequently, a method based on bidirectional long short-term
memory (BLSTM) with a 2-dimensional convolutional neural network (CNN) is
proposed to capture sequential writing styles for authorship attribution. The
BLSTM was used to obtain the sequential relationship among characteristics
using subword information. The 2-dimensional CNN was applied to understand the
local syntactical position of the style from unlabeled input text. The proposed
method was experimentally evaluated against numerous state-of-the-art methods
across the public corporal of CCAT50, IMDb62, Blog50, and Twitter50.
Experimental results indicate accuracy improvement of 1.07\%, and 0.96\% on
CCAT50 and Twitter, respectively, and produce comparable results on the
remaining datasets.Comment: 8 pages, 4 figur
Efficiency of histidine rich protein II-based rapid diagnostic tests for monitoring malaria transmission intensities in an endemic area
No full textIn recent years there has been a global decrease in the prevalence of malaria due to scaling up of control measures,
hence global control efforts now target elimination and eradication of the disease. However, a major problem associated
with elimination is asymptomatic reservoir of infection especially in endemic areas. This study aims to determine the
efficiency of histidine rich protein II (HRP-2) based rapid diagnostic tests (RDT) for monitoring transmission intensities in
an endemic community in Nigeria during the pre-elimination stage. Plasmodium falciparum asymptomatic malaria
infection in healthy individuals and symptomatic cases were detected using HRP-2. RDT negative tests were re-checked
by microscopy and by primer specific PCR amplification of merozoite surface protein 2 (msp-2) for asexual parasites and
Pfs25 gene for gametocytes in selected samples to detect low level parasitemia undetectable by microscopy. The mean age
of the study population (n=280) was 6.12 years [95% CI 5.16 – 7.08, range 0.5 – 55], parasite prevalence was 44.6% and
36.3% by microscopy and RDT respectively (p =0.056). The parasite prevalence of 61.5% in children aged >2 – 10 years
was significantly higher than 3.7% rate in adults >18years (p < 0.0001, χ2 = 60.45). RDT detected additional 29.6%
asymptomatic cases but a lower specificity of 68.8% in symptomatic carriers. In 15 selected RDT positive samples, only 6
were positive by PCR and no gametocyte was detected. The results indicate that HRP-2 RDTs are a vital tool for
understanding transmission dynamics and detecting immune-suppressed, recent and asymptomatic infections, thus crucial
to tackle low level transmission and eliminating malaria in endemic areas
