A5009782240- Sentiment Analysis and Opinion Mining
- Advanced Text Analysis Techniques
- Topic Modeling
- Privacy, Security, and Data Protection
- Natural Language Processing Techniques
- Mental Health via Writing
- Digital Mental Health Interventions
- COVID-19 Digital Contact Tracing
- Impact of Technology on Adolescents
- Mathematics, Computing, and Information Processing
- Misinformation and Its Impacts
- Suicide and Self-Harm Studies
- Spam and Phishing Detection
- Cybercrime and Law Enforcement Studies
- Mental Health Research Topics
- Healthcare Systems and Practices
- Urban Transport and Accessibility
- Network Security and Intrusion Detection
- Advanced Malware Detection Techniques
- Data Quality and Management
- Technology and Data Analysis
- Recommender Systems and Techniques
- Web Data Mining and Analysis
- Text and Document Classification Technologies
- Expert finding and Q&A systems
Aston University
2022-2024
Laboratoire d’Informatique et Systèmes
2016-2023
Centre National de la Recherche Scientifique
2016-2023
Université de Toulon
2017-2023
University of Strathclyde
2020-2022
University of Edinburgh
2022
Northumbria University
2022
University Ucinf
2020-2021
Château Gombert
2016-2018
Aix-Marseille Université
2016-2018
In this paper, we present our contribution in SemEval2016 task7 1 : Determining Sentiment Intensity of English and Arabic Phrases, where use web search engines for unsupervised sentiment intensity prediction.Our work is based, first, on a group classic lexicons (e.g.Sen-timent140 Lexicon, SentiWordNet).Second, engines' ability to find the cooccurrence sentences with predefined negative positive words.The (e.g.Google Search API) enhance results phrases built from opposite polarity terms.
When pieces from an individual's personal information available online are connected over time and across multiple platforms, this more complete digital trace can give unintended insights into their life opinions. In a data narrative interview study with 26 currently employed participants, we examined risks harms to individuals employers when others joined the dots between information. We discuss themes of visibility self-disclosure, unintentional leakage privacy literacies constructed our...
We present, in this paper, our contribution SemEval2017 task 4 : “Sentiment Analysis Twitter”, subtask A: “Message Polarity Classification”, for English and Arabic languages. Our system is based on a list of sentiment seed words adapted tweets. The relations between other terms are captured by cosine similarity the word embedding representations (word2vec). These extracted from datasets annotated tweets available online. tests, using these words, show significant improvement results compared...
Book search is a challenging task due to discrepancies between the content and description of books, on one side, ways in which people query for other. However, online reviewers provide an opinionated book, with alternative features that describe emotional experiential aspects book. Therefore, locating sentences within reviews, could rich source evidence help improve book recommendations. Specifically, sentiment analysis (SA) be employed identify salient terms, then used expansion? This...
Travel safety for women is a concern, particularly in India, where gender-based violence and harassment are significant issues. This study examines how the perception of influences women’s travel behaviour assesses potential technology solutions to ensure their safety. Additionally, it explores AI machine learning techniques may be leveraged enhance A comprehensive mobility survey was designed uncover complex relationship between behaviour, reasons mode choice, built environment, feelings,...
The law does not concern itself with trifles. If a risk is deemed minimal, or an infraction negligible, invoking the authority of often seems unnecessary. However, there are increasingly fields human activity where this principle leads to gaps in protection necessary for flourishing society. This paper reports findings and ideas from research project cumulative data disclosure, aggregation themselves harmless points can expose users social media significant personal risk.
Abstract Every day, people post information about themselves and others on online social networks, making such accessible within their circles but also, potentially, way beyond. While the posted may seem benign or innocuous, small pieces of information, when tied together, can potentially reveal much more person than intended. Such cumulative revelations could expose them to risks as identity theft, fraud loss employment. This paper describes findings from interviews people's interactions,...
Small pieces of data that are shared online, over time and across multiple social networks, have the potential to reveal more cumulatively than a person intends. This could result in harm, loss or detriment them depending what information is revealed, who can access it, how it processed. But aware network users much they actually disclosing? And if examine all their data, cumulative revelations might be found potentially increase risk various online threats (social engineering, fraud,...
Text normalisation is a necessity to correctand make more sense of the micro-blogs messages, for information retrieval purposes. Unfortunately, tools and resources text normalization are rarely shared. In this paper, an approach presented based onan unsupervised method using distributed representations words, known also as "word embedding", applied on Arabic, French English Languages. addition, tool will be supplied create dictionaries normalisation, in form pairs misspelled word with its...
Sentiment analysis is central to the process of mining opinions and attitudes from online texts. While much attention has been paid sentiment classification problem, less work tried tackle problem predicting intensity sentiment. The go method VADER --- an unsupervised lexicon based approach scoring However, such approaches are limited because vocabulary mismatch problem. In this paper, we present in detail evaluate our AWESSOME framework (A Word Embedding Scorer Of Many Emotions) for...