Displaying all 12 publications

Abstract:
Sort:
  1. Lu J, Chua SN, Kavanaugh JR, Prashar J, Ndip-Agbor E, Santoso M, et al.
    Am J Prev Med, 2024 Dec;67(6):811-819.
    PMID: 39306774 DOI: 10.1016/j.amepre.2024.08.006
    INTRODUCTION: Starting June 30, 2022, Google implemented its revised Inappropriate Content Advertising Policy, targeting discriminatory skin-lightening ads that suggest superiority of certain skin shades. This study evaluates the ad content changes from 2 weeks before to 2 weeks after the policy's enforcement.

    METHODS: Text ads from Google searches in eight countries (Bahamas, Germany, India, Malaysia, Mexico, South Africa, United Arab Emirates, and United States) were collected in 2022, totaling 1,974 prepolicy and 3,262 post-policy ads, and analyzed in 2023. A gold standard database was established by two coders who labeled 707 ads, which trained five natural language processing models to label the ads, covering content and target demographics. The descriptive statistics and multivariable logistic models were applied to analyze content before versus after policy implementation, both globally and by country.

    RESULTS: Vertex AI emerged as the best natural language processing model with the highest F1 score of 0.87. There were significant decreases from pre- to post-policy implementation in the prevalence of labels of "Racial or Ethnic Identification" and "Ingredients: Natural" by 47% and 66%, respectively. Notable differences were identified from pre- to post-policy implementation in India, Mexico, and Germany.

    CONCLUSIONS: The study observed changes in skin-lightening product advertisement labels from pre- to post-policy implementation, both globally and within countries. Considering the influence of digital advertising on colorist norms, assessing digital ad policy changes is crucial for public health surveillance. This study presents a computational method to help monitor digital platform policies for consumer product advertisements that affect public health.

    Matched MeSH terms: Natural Language Processing*
  2. Abed SA, Tiun S, Omar N
    PLoS One, 2015;10(9):e0136614.
    PMID: 26422368 DOI: 10.1371/journal.pone.0136614
    Word Sense Disambiguation (WSD) is the task of determining which sense of an ambiguous word (word with multiple meanings) is chosen in a particular use of that word, by considering its context. A sentence is considered ambiguous if it contains ambiguous word(s). Practically, any sentence that has been classified as ambiguous usually has multiple interpretations, but just one of them presents the correct interpretation. We propose an unsupervised method that exploits knowledge based approaches for word sense disambiguation using Harmony Search Algorithm (HSA) based on a Stanford dependencies generator (HSDG). The role of the dependency generator is to parse sentences to obtain their dependency relations. Whereas, the goal of using the HSA is to maximize the overall semantic similarity of the set of parsed words. HSA invokes a combination of semantic similarity and relatedness measurements, i.e., Jiang and Conrath (jcn) and an adapted Lesk algorithm, to perform the HSA fitness function. Our proposed method was experimented on benchmark datasets, which yielded results comparable to the state-of-the-art WSD methods. In order to evaluate the effectiveness of the dependency generator, we perform the same methodology without the parser, but with a window of words. The empirical results demonstrate that the proposed method is able to produce effective solutions for most instances of the datasets used.
    Matched MeSH terms: Natural Language Processing*
  3. Tan WM, Ng WL, Ganggayah MD, Hoe VCW, Rahmat K, Zaini HS, et al.
    Health Informatics J, 2023;29(3):14604582231203763.
    PMID: 37740904 DOI: 10.1177/14604582231203763
    Radiology reporting is narrative, and its content depends on the clinician's ability to interpret the images accurately. A tertiary hospital, such as anonymous institute, focuses on writing reports narratively as part of training for medical personnel. Nevertheless, free-text reports make it inconvenient to extract information for clinical audits and data mining. Therefore, we aim to convert unstructured breast radiology reports into structured formats using natural language processing (NLP) algorithm. This study used 327 de-identified breast radiology reports from the anonymous institute. The radiologist identified the significant data elements to be extracted. Our NLP algorithm achieved 97% and 94.9% accuracy in training and testing data, respectively. Henceforth, the structured information was used to build the predictive model for predicting the value of the BIRADS category. The model based on random forest generated the highest accuracy of 92%. Our study not only fulfilled the demands of clinicians by enhancing communication between medical personnel, but it also demonstrated the usefulness of mineable structured data in yielding significant insights.
    Matched MeSH terms: Natural Language Processing*
  4. Xiao H
    Neural Netw, 2020 Nov;131:172-184.
    PMID: 32801109 DOI: 10.1016/j.neunet.2020.07.024
    Paraphrase identification serves as an important topic in natural language processing while sequence alignment and matching underlie the principle of this task. Traditional alignment methods take advantage of attention mechanism. Attention mechanism, i.e. weighting technique, could pick out the most similar/dissimilar parts, but is weak in modeling the aligned unmatched parts, which are the crucial evidence to identify paraphrases. In this paper, we empower neural architecture with Hungarian algorithm to extract the aligned unmatched parts. Specifically, first, our model applies BiLSTM/BERT to encode the input sentences into hidden representations. Then, Hungarian layer leverages the hidden representations to extract the aligned unmatched parts. Last, we apply cosine similarity to metric the aligned unmatched parts for a final discrimination. Extensive experiments show that our model outperforms other baselines, substantially and significantly.
    Matched MeSH terms: Natural Language Processing
  5. He Y, Tom Abdul Wahab NE, Muhamad H, Liu D
    PLoS One, 2024;19(2):e0296910.
    PMID: 38381720 DOI: 10.1371/journal.pone.0296910
    BACKGROUND: With the evolution of China's social structure and values, there has been a shift in attitudes towards marriage and fertility, with an increasing number of women holding diverse perspectives on these matters. In order to better comprehend the fundamental reasons behind these attitude changes and to provide a basis for targeted policymaking, this study employs natural language processing techniques to analyze the discourse of Chinese women.

    METHODS: The study focused on analyzing 3,200 comments from Weibo, concentrating on six prominent topics linked to women's marriage and fertility. These topics were treated as research cases. The research employed natural language processing techniques, such as sentiment orientation analysis, Word2Vec, and TextRank.

    RESULTS: Firstly, the overall sentiment orientation of Chinese women toward marriage and fertility was largely pessimistic. Secondly, the factors contributing to this negative sentiment were categorized into four dimensions: social policies and rights protection, concerns related to parenting, values and beliefs associated with marriage and fertility, and family and societal culture.

    CONCLUSION: Based on these outcomes, the study proposed a range of mechanisms and pathways to enhance women's sentiment orientation towards marriage and fertility. These mechanisms encompass safeguarding women and children's rights, promoting parenting education, providing positive guidance on social media, and cultivating a diverse and inclusive social and cultural environment. The objective is to offer precise and comprehensive reference points for the formulation of policies that align more effectively with practical needs.

    Matched MeSH terms: Natural Language Processing*
  6. Arnulf JK, Larsen KR, Martinsen ØL, Bong CH
    PLoS One, 2014;9(9):e106361.
    PMID: 25184672 DOI: 10.1371/journal.pone.0106361
    Some disciplines in the social sciences rely heavily on collecting survey responses to detect empirical relationships among variables. We explored whether these relationships were a priori predictable from the semantic properties of the survey items, using language processing algorithms which are now available as new research methods. Language processing algorithms were used to calculate the semantic similarity among all items in state-of-the-art surveys from Organisational Behaviour research. These surveys covered areas such as transformational leadership, work motivation and work outcomes. This information was used to explain and predict the response patterns from real subjects. Semantic algorithms explained 60-86% of the variance in the response patterns and allowed remarkably precise prediction of survey responses from humans, except in a personality test. Even the relationships between independent and their purported dependent variables were accurately predicted. This raises concern about the empirical nature of data collected through some surveys if results are already given a priori through the way subjects are being asked. Survey response patterns seem heavily determined by semantics. Language algorithms may suggest these prior to administering a survey. This study suggests that semantic algorithms are becoming new tools for the social sciences, opening perspectives on survey responses that prevalent psychometric theory cannot explain.
    Matched MeSH terms: Natural Language Processing
  7. R.U GOBITHAASAN, NUR FARHANA SYAHIRA CHE HAMID
    MyJurnal
    Sentiment analysis is a field of research that has a significant impact on today’s nations, politics and businesses. It is an algorithmic process to comprehend the opinions of a given subject based on the Natural Language Processing (NLP) methodologies. It has received much attention in recent years and is proven vital in various fields, e.g., online product reviews and social media analysis (Twitter, Facebook, etc.). This paper reports the outcome of sentiment analysis to investigate people’s acceptance of Pakatan Harapan, as the new Malaysian government, spearheaded by Tun Dr. Mahathir Mohamad and Dr. Wan Azizah, with an influence of Dato Seri Anwar Ibrahim. The objective is to classify tweets into three types of sentiments; positive, neutral and negative using Naïve Bayes method which is readily available in Python. The first step is tweets extraction for a month (March to April 2019) using search queries: {Pakatan Harapan, Mahathir, Anwar Ibrahim, Wan Azizah}. It is followed by tweets wrangling using NLP library and lastly output visualization in the form of a word cloud. A word cloud is a visual representation of text data with various font sizes depending on its probabilities. Final results showed that the tweets related to new government consist of neutral sentiment (41%) followed by positive sentiment (30%) and negative sentiment (29%). Malaysians do prefer the new government. However careful mitigation steps must be crafted to overcome controversial issues such as the ‘Rome Statute’ to avoid negative digital footprint, hence winning the Malaysians’ heart.
    Matched MeSH terms: Natural Language Processing
  8. Lutfi SL, Fernández-Martínez F, Lorenzo-Trueba J, Barra-Chicote R, Montero JM
    Sensors (Basel), 2013;13(8):10519-38.
    PMID: 23945740 DOI: 10.3390/s130810519
    We describe the work on infusion of emotion into a limited-task autonomous spoken conversational agent situated in the domestic environment, using a need-inspired task-independent emotion model (NEMO). In order to demonstrate the generation of affect through the use of the model, we describe the work of integrating it with a natural-language mixed-initiative HiFi-control spoken conversational agent (SCA). NEMO and the host system communicate externally, removing the need for the Dialog Manager to be modified, as is done in most existing dialog systems, in order to be adaptive. The first part of the paper concerns the integration between NEMO and the host agent. The second part summarizes the work on automatic affect prediction, namely, frustration and contentment, from dialog features, a non-conventional source, in the attempt of moving towards a more user-centric approach. The final part reports the evaluation results obtained from a user study, in which both versions of the agent (non-adaptive and emotionally-adaptive) were compared. The results provide substantial evidences with respect to the benefits of adding emotion in a spoken conversational agent, especially in mitigating users' frustrations and, ultimately, improving their satisfaction.
    Matched MeSH terms: Natural Language Processing*
  9. Aljunid SM, Rodrigues JM, Best L, Ahmed Z, Reeza Mustaffa H, Trombert B, et al.
    PMID: 26262389
    Casemix grouping using procedures classifications has become an important use case for health care terminologies. There are so many different national procedures classifications used for Casemix grouping that it is not possible to agree on a worldwide standard. ICHI (International Classification of Health Interventions) is proposing an approach that standardises only the terminologies' model structure. The poster shows the use of the ICHI alpha to replace ICD9 CM Volume 3 in the UNU-CBG International Casemix grouper.
    Matched MeSH terms: Natural Language Processing*
  10. Mujtaba G, Shuib L, Raj RG, Rajandram R, Shaikh K
    J Forensic Leg Med, 2018 Jul;57:41-50.
    PMID: 29801951 DOI: 10.1016/j.jflm.2017.07.001
    OBJECTIVES: Automatic text classification techniques are useful for classifying plaintext medical documents. This study aims to automatically predict the cause of death from free text forensic autopsy reports by comparing various schemes for feature extraction, term weighing or feature value representation, text classification, and feature reduction.

    METHODS: For experiments, the autopsy reports belonging to eight different causes of death were collected, preprocessed and converted into 43 master feature vectors using various schemes for feature extraction, representation, and reduction. The six different text classification techniques were applied on these 43 master feature vectors to construct a classification model that can predict the cause of death. Finally, classification model performance was evaluated using four performance measures i.e. overall accuracy, macro precision, macro-F-measure, and macro recall.

    RESULTS: From experiments, it was found that that unigram features obtained the highest performance compared to bigram, trigram, and hybrid-gram features. Furthermore, in feature representation schemes, term frequency, and term frequency with inverse document frequency obtained similar and better results when compared with binary frequency, and normalized term frequency with inverse document frequency. Furthermore, the chi-square feature reduction approach outperformed Pearson correlation, and information gain approaches. Finally, in text classification algorithms, support vector machine classifier outperforms random forest, Naive Bayes, k-nearest neighbor, decision tree, and ensemble-voted classifier.

    CONCLUSION: Our results and comparisons hold practical importance and serve as references for future works. Moreover, the comparison outputs will act as state-of-art techniques to compare future proposals with existing automated text classification techniques.

    Matched MeSH terms: Natural Language Processing
  11. Abdullah AA, Altaf-Ul-Amin M, Ono N, Sato T, Sugiura T, Morita AH, et al.
    Biomed Res Int, 2015;2015:139254.
    PMID: 26495281 DOI: 10.1155/2015/139254
    Volatile organic compounds (VOCs) are small molecules that exhibit high vapor pressure under ambient conditions and have low boiling points. Although VOCs contribute only a small proportion of the total metabolites produced by living organisms, they play an important role in chemical ecology specifically in the biological interactions between organisms and ecosystems. VOCs are also important in the health care field as they are presently used as a biomarker to detect various human diseases. Information on VOCs is scattered in the literature until now; however, there is still no available database describing VOCs and their biological activities. To attain this purpose, we have developed KNApSAcK Metabolite Ecology Database, which contains the information on the relationships between VOCs and their emitting organisms. The KNApSAcK Metabolite Ecology is also linked with the KNApSAcK Core and KNApSAcK Metabolite Activity Database to provide further information on the metabolites and their biological activities. The VOC database can be accessed online.
    Matched MeSH terms: Natural Language Processing
  12. Othman RM, Deris S, Illias RM
    J Biomed Inform, 2008 Feb;41(1):65-81.
    PMID: 17681495
    A genetic similarity algorithm is introduced in this study to find a group of semantically similar Gene Ontology terms. The genetic similarity algorithm combines semantic similarity measure algorithm with parallel genetic algorithm. The semantic similarity measure algorithm is used to compute the similitude strength between the Gene Ontology terms. Then, the parallel genetic algorithm is employed to perform batch retrieval and to accelerate the search in large search space of the Gene Ontology graph. The genetic similarity algorithm is implemented in the Gene Ontology browser named basic UTMGO to overcome the weaknesses of the existing Gene Ontology browsers which use a conventional approach based on keyword matching. To show the applicability of the basic UTMGO, we extend its structure to develop a Gene Ontology -based protein sequence annotation tool named extended UTMGO. The objective of developing the extended UTMGO is to provide a simple and practical tool that is capable of producing better results and requires a reasonable amount of running time with low computing cost specifically for offline usage. The computational results and comparison with other related tools are presented to show the effectiveness of the proposed algorithm and tools.
    Matched MeSH terms: Natural Language Processing
Filters
Contact Us

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links