Low Resource Social Media Text Mining

This book focuses on methods that are unsupervised or require minimal supervision—vital in the low-resource domain. Over the past few years, rapid growth in Internet access across the globe has resulted in an explosion in user-generated text content in social media platforms. This effect is significantly pronounced in linguistically diverse areas of the world like South Asia, where over 400 million people regularly access social media platforms. YouTube, Facebook, and Twitter report a monthly active user base in excess of 200 million from this region. Natural language processing (NLP) research and publicly available resources such as models and corpora prioritize Web content authored primarily by a Western user base. Such content is authored in English by a user base fluent in the language and can be processed by a broad range of off-the-shelf NLP tools. In contrast, text from linguistically diverse regions features high levels of multilinguality, code-switching, and varied language skill levels. Resources like corpora and models are also scarce. Due to these factors, newer methods are needed to process such text. This book is designed for NLP practitioners well versed in recent advances in the field but unfamiliar with the landscape of low-resource multilingual NLP. The contents of this book introduce the various challenges associated with social media content, quantify these issues, and provide solutions and intuition. When possible, the methods discussed are evaluated on real-world social media data sets to emphasize their robustness to the noisy nature of the social media environment. On completion of the book, the reader will be well-versed with the complexity of text-mining in multilingual, low-resource environments; will be aware of a broad set of off-the-shelf tools that can be applied to various problems; and will be able to conduct sophisticated analyses of such text.

This book focuses on methods that are unsupervised or require minimal supervision-vital in the low-resource domain. Over the past few years, rapid growth in Internet access across the globe has resulted in an explosion in user-generated text content in social media platforms. This effect is significantly pronounced in linguistically diverse areas of the world like South Asia, where over 400 million people regularly access social media platforms. YouTube, Facebook, and Twitter report a monthly active user base in excess of 200 million from this region. Natural language processing (NLP) research and publicly available resources such as models and corpora prioritize Web content authored primarily by a Western user base. Such content is authored in English by a user base fluent in the language and can be processed by a broad range of off-the-shelf NLP tools. In contrast, text from linguistically diverse regions features high levels of multilinguality, code-switching, and varied language skill levels. Resources like corpora and models are also scarce. Due to these factors, newer methods are needed to process such text. This book is designed for NLP practitioners well versed in recent advances in the field but unfamiliar with the landscape of low-resource multilingual NLP. The contents of this book introduce the various challenges associated with social media content, quantify these issues, and provide solutions and intuition. When possible, the methods discussed are evaluated on real-world social media data sets to emphasize their robustness to the noisy nature of the social media environment. On completion of the book, the reader will be well-versed with the complexity of text-mining in multilingual, low-resource environments; will be aware of a broad set of off-the-shelf tools that can be applied to various problems; and will be able to conduct sophisticated analyses of such text.

This book constitutes refereed proceedings from the First International Conference on Speech and Language Technologies for Low-resource Languages, SPELLL 2022, held in Kalavakkam, India, in November 2022. The 25 presented papers were thoroughly reviewed and selected from 70 submissions. The papers are organised in the following topical sections: ​language resources; language technologies; speech technologies; multimodal data analysis; fake news detection in low-resource languages (regional-fake); low resource cross-domain, cross-lingualand cross-modal offensie content analysis (LC4).

In our increasingly interconnected world, low-resource languages face the threat of oblivion. These linguistic gems, often spoken by marginalized communities, are at risk of fading away due to limited data and resources. The neglect of these languages not only erodes cultural diversity but also hinders effective communication, education, and social inclusion. Academics, practitioners, and policymakers grapple with the urgent need for a comprehensive solution to preserve and empower these vulnerable languages. Empowering Low-Resource Languages With NLP Solutions is a pioneering book that stands as the definitive answer to the pressing problem at hand. It tackles head-on the challenges that low-resource languages face in the realm of Natural Language Processing (NLP). Through real-world case studies, expert insights, and a comprehensive array of topics, this book equips its readers—academics, researchers, practitioners, and policymakers—with the tools, strategies, and ethical considerations needed to address the crisis facing low-resource languages.

This is the ideal introduction for students seeking to collect and analyze textual data from online sources. It covers the most critical issues that they must take into consideration at all stages of their research projects.

This second edition of Digital Analytics for Marketing provides students with a comprehensive overview of the tools needed to measure digital activity and implement best practices when using data to inform marketing strategy. It is the first text of its kind to introduce students to analytics platforms from a practical marketing perspective. Demonstrating how to integrate large amounts of data from web, digital, social, and search platforms, this helpful guide offers actionable insights into data analysis, explaining how to "connect the dots" and "humanize" information to make effective marketing decisions. The authors cover timely topics, such as social media, web analytics, marketing analytics challenges, and dashboards, helping students to make sense of business measurement challenges, extract insights, and take effective actions. The book’s experiential approach, combined with chapter objectives, summaries, and review questions, will engage readers, deepening their learning by helping them to think outside the box. Filled with engaging, interactive exercises and interesting insights from industry experts, this book will appeal to undergraduate and postgraduate students of digital marketing, online marketing, and analytics. Online support materials for this book include an instructor’s manual, test bank, and PowerPoint slides.