Search results for "Profiling"

showing 10 items of 881 documents

Improving Irony and Stereotype Spreaders Detection using Data Augmentation and Convolutional Neural Network

2022

In this paper we describe a deep learning model based on a Data Augmentation (DA) layer followed by a Convolutional Neural Network (CNN). The proposed model was developed by our team for the Profiling Irony and Stereotype Spreaders (ISSs) task proposed by the PAN 2022 organizers. As a first step, to classify an author as ISS or not (nISS), we developed a DA layer that expands each sample in the dataset provided. Using this augmented dataset we trained the CNN. Then, to submit our predictions, we apply our DA layer on the samples within the unlabeled test set too. Finally we fed our trained CNN with the augmented test set to generate our final predictions. To develop and test our model we us…

Settore ING-INF/03 - Telecomunicazioniauthor profiling convolutional neural network data augmentation irony stereotypes text classification Twitter
researchProduct

User Activity Recognition via Kinect in an Ambient Intelligence Scenario

2014

The availability of an ever-increasing kind of cheap, unobtrusive, sensing devices has stressed the need for new approaches to merge raw measurements in order to realize what is happening in the monitored environment. Ambient Intelligence (AmI) techniques exploit information about the environment state to adapt the environment itself to the users’ preferences. Even if traditional sensors allow a rough understanding of the users’ preferences, ad-hoc sensors are required to obtain a deeper comprehension of users’ habits and activities. In this paper we propose a framework to recognize users’ activities via a depth and RGB camera device, namely the Microsoft Kinect. The proposed approach takes…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniEngineeringKinectAmbient intelligenceAmbient IntelligenceExploitbusiness.industryUser ProfilingActivity Recognitioncomputer.software_genreActivity recognitionSupport vector machineHuman–computer interactionData miningCluster analysisbusinessMerge (version control)computerIERI Procedia
researchProduct

Towards Partners Profiling in Human Robot Interaction Contexts

2012

Individuality is one of the most important qualities of humans. Social robots should be able to model the individuality of the human partners and to modify their behaviours accordingly.This paper proposes a profiling system for social robots to be able to learn the individuality of human partners in social contexts. Profiles are expressed in terms of of identities and preferences bound together. In particular, people’s identity is captured by the use of facial features, while preferences are extracted from the discussion between the partners. Both are bound using an Hebb network. Experiments show the feasibility and the performances of the approach presented.

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniPersonal robotSocial robotComputer sciencebusiness.industryHuman–robot interactionHuman–computer interactionpersonal robotsProfiling (information science)Artificial intelligencehuman robot interactionprofilingbusinessprofiling personal robots human robot interactionprofiling; personal robots; human robot interaction
researchProduct

Detection of Points of Interest in a Smart Campus

2019

Understanding users' habits is a critical task in order to develop advanced services, such as personalized recommendation and virtual assistance. In this work, we propose a novel approach to detect Points of Interest visited by users of a campus, by using mobility traces collected through users' smartphones. Our method takes advantage of the intentional and recurrent nature of human movements to build up mobility profiles, and combines different machine learning methods to merge sensory information with the past users' behavior. The proposed approach has been validated on a synthetic dataset and the experimental results show its effectiveness.

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniPoint of interestHuman–computer interactionComputer scienceSmart CampuSmart Campus PoI Automatic Detection Human Mobility ProfilingSmart CampusPoI Automatic DetectionSmart campusMerge (version control)Human Mobility Profiling
researchProduct

T100: A modern classic ensemble to profile irony and stereotype spreaders

2022

In this work we propose a novel ensemble model based on deep learning and non-deep learning classifiers. The proposed model was developed by our team for participating at the Profiling Irony and Stereotype Spreaders (ISSs) task hosted at PAN@CLEF2022. Our ensemble (named T100), include a Logistic Regressor (LR) that classifies an author as ISS or not (nISS) considering the predictions provided by a first stage of classifiers. All these classifiers are able to reach state-of-the-art results on several text classification tasks. These classifiers (namely, the voters) are a Convolutional Neural Network (CNN), a Support Vector Machine (SVM), a Decision Tree (DT) and a Naive Bayes (NB) classifie…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniSettore ING-INF/03 - Telecomunicazioniirony stereotypes author profiling text classification Twitter ensemble logistic regressor
researchProduct

Fake News Spreaders Detection: Sometimes Attention Is Not All You Need

2022

Guided by a corpus linguistics approach, in this article we present a comparative evaluation of State-of-the-Art (SotA) models, with a special focus on Transformers, to address the task of Fake News Spreaders (i.e., users that share Fake News) detection. First, we explore the reference multilingual dataset for the considered task, exploiting corpus linguistics techniques, such as chi-square test, keywords and Word Sketch. Second, we perform experiments on several models for Natural Language Processing. Third, we perform a comparative evaluation using the most recent Transformer-based models (RoBERTa, DistilBERT, BERT, XLNet, ELECTRA, Longformer) and other deep and non-deep SotA models (CNN,…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazionitext classificationcorpus linguisticSettore ING-INF/03 - Telecomunicazionifake newTwitterauthor profilingconvolutional neural networkdeep learningNatural Language Processing (NLP)user classificationfake news; misinformation; Natural Language Processing (NLP); transformers; Twitter; convolutional neural networks; text classification; deep learning; machine learning; user classification; author profiling; corpus linguistics; linguistic analysismachine learningtransformermisinformationlinguistic analysisInformation Systems
researchProduct

miRNA Signature and Dicer Requirement during Human Endometrial Stromal Decidualization In Vitro

2012

Decidualization is a morphological and biochemical transformation of endometrial stromal fibroblast into differentiated decidual cells, which is critical for embryo implantation and pregnancy establishment. The complex regulatory networks have been elucidated at both the transcriptome and the proteome levels, however very little is known about the post-transcriptional regulation of this process. miRNAs regulate multiple physiological pathways and their de-regulation is associated with human disorders including gynaecological conditions such as endometriosis and preeclampsia. In this study we profile the miRNAs expression throughout human endometrial stromal (hESCs) decidualization and analy…

Sexual ReproductionRibonuclease IIISmall interfering RNAAnatomy and PhysiologyCellular differentiationGene ExpressionBioinformaticsCell morphologyTranscriptomeEndocrinologyMolecular Cell BiologyMultidisciplinarybiologyStem CellsQDeciduaRObstetrics and GynecologyCell DifferentiationForkhead Transcription FactorsCell biologyFemale Genital Diseasesmedicine.anatomical_structureMedicineFemaleResearch ArticleAdultScienceMolecular GeneticsYoung AdultmicroRNAGeneticsDeciduamedicineReproductive EndocrinologyHumansGene RegulationBiologyEmbryonic Stem CellsHomeodomain ProteinsGene Expression ProfilingReproductive SystemComputational BiologyDecidualizationFibroblastsFemale SubfertilityInsulin-Like Growth Factor Binding Protein 1MicroRNAsHomeobox A10 ProteinsGene Expression Regulationbiology.proteinStromal CellsDevelopmental BiologyDicerPLoS ONE
researchProduct

Transcriptomic identification of miR-205 target genes potentially involved in metastasis and survival of cutaneous malignant melanoma

2020

AbstractCutaneous melanoma is an aggressive neoplasm and is responsible for the majority of skin cancer deaths. Several miRNAs are involved in melanoma tumor progression. One of them is miR-205, the loss of which contributes to the development of melanoma metastasis. We evaluated whole-genome mRNA expression profiling associated with different miR-205 expression levels in melanoma cells. Differential expression analysis identified 243 differentially expressed transcripts including inositol polyphosphate 5′-phosphatase-like protein-1 (INPPL1) and BTB/POZ Domain-Containing Protein 3 (BTBD3). INPPL1 and BTBD3 were downregulated when melanoma cells expressed miR-205, indicating that these genes…

Skin NeoplasmsDown-Regulationlcsh:MedicineNerve Tissue ProteinsBiologyArticleDisease-Free SurvivalMetastasisTranscriptomeCancer epigeneticsmicroRNATumor Cells CulturedmedicineHumansNeoplasm MetastasisCàncerlcsh:Science3' Untranslated RegionsMelanomaLymph nodeMultidisciplinaryGene Expression ProfilingMelanomalcsh:Rmedicine.diseaseGene Expression Regulation NeoplasticMicroRNAsmedicine.anatomical_structureTumor progressionLymphatic MetastasisPhosphatidylinositol-345-Trisphosphate 5-PhosphatasesCutaneous melanomaCancer researchlcsh:QSkin cancerTranscriptomeScientific Reports
researchProduct

Aberrant methylation of tRNAs links cellular stress to neuro-developmental disorders.

2014

Mutations in the cytosine-5 RNA methyltransferase NSun2 cause microcephaly and other neurological abnormalities in mice and human. How post-transcriptional methylation contributes to the human disease is currently unknown. By comparing gene expression data with global cytosine-5 RNA methylomes in patient fibroblasts and NSun2-deficient mice, we find that loss of cytosine-5 RNA methylation increases the angiogenin-mediated endonucleolytic cleavage of transfer RNAs (tRNA) leading to an accumulation of 5' tRNA-derived small RNA fragments. Accumulation of 5' tRNA fragments in the absence of NSun2 reduces protein translation rates and activates stress pathways leading to reduced cell siz…

Small RNARNA methylationBiologyNSun2MethylationGeneral Biochemistry Genetics and Molecular Biology03 medical and health sciencesMisuMice0302 clinical medicineRNA TransferGene expressionAnimalsHumans5‐methylcytidine ; Misu ; Nsun2 ; Rna ModificationMolecular Biology030304 developmental biology5-methylcytidineRegulation of gene expression0303 health sciencesTRNA methylationGeneral Immunology and MicrobiologyGeneral NeuroscienceGene Expression ProfilingRNABrainArticlesMethylationMethyltransferasesRibonuclease PancreaticRNA modificationMolecular biologyOxidative StressGene Expression RegulationTransfer RNANervous System Diseases030217 neurology & neurosurgery5‐methylcytidine
researchProduct

Smartphone Usage Among Millennial in Finland and Implications for Marketing Segmentation Strategies: Lessons for Nigeria

2018

The study examines smart phone usage by millennials based on different criteria of operating system, Wi-Fi, text messaging, internet surfing and social media. The study used quantitative methodology and data were gathered with online questionnaires with 391 young smartphone users in Finland. The Millennial were clustered into five levels. The results reveal the prominent status of profiling in a developed market and how marketers in emerging markets can apply segmentation and targeting strategies using instant messaging, text messages, email, mobile app, gamification and social media based on the profile of each segment. Nigerian policy makers should adopt a framework to make smartphone aff…

Smart phoneInternet privacyNigeriasosiaalinen media050801 communication & media studiesComputer-assisted web interviewingMillennialsmartphone0508 media and communicationsMarket segmentationSuomi0502 economics and businessProfiling (information science)Social mediaDeveloped marketEmerging marketstargetingFinlandbusiness.industry05 social scienceskohderyhmätälypuhelimetsegmentointimarkkinointi050211 marketingThe InternetBusiness
researchProduct