Chemical Named Entity Recognition Using Deep Learning Techniques

Chemical entities can be represented in different forms like chemical names, chemical formulae, and chemical structures. Because of the different classification frameworks for chemical names, the task of distinguishing proof or extraction of chemical elements with less ambiguous is considered a major test. Compound named entity recognition (NER) is the initial phase in any chemical-related data extraction strategy. The majority of the chemical NER is done utilizing dictionary-based, rule-based, and machine learning procedures. Recently, deep learning methods have evolved, and, in this chapter, the authors sketch out the various deep learning techniques applied for chemical NER. First, the authors introduced the fundamental concepts of chemical named entity recognition, the textual contents of chemical documents, and how these chemicals are represented in chemical literature. The chapter concludes with the strengths and weaknesses of the above methods and also the types of the chemical entities extracted.

Significance of Natural Language Processing in Data Analysis Using Business Intelligence

In the current machine-centric world, humans expect a lot from machines right from waking us up. We expect them to do activities like reminding us on traffic, tracking of appointments, etc. The smart devices we have with us are creating a constructive impact on our day-to-day lives. Many of us have not thought about the communication between ourselves and the devices we have and the language we use for communication. Natural language processing runs behind all these activities and is currently playing a vital role with respect to the communication with humans with the use of virtual assistants like Alexa, Siri, and search engines like Bing, Google, etc. This implies that we are talking with the machines as if they are human. The advanced natural language processing techniques have drastically modified the way to discover and interact with data. In the recent world, the same advanced techniques are primarily used in the data analysis using NLP in business intelligence tools. This chapter elaborates the significance of natural language processing in business intelligence.

Text Mining Using Twitter Data

The microblogging social networking service Twitter has been abuzz around the globe in the last decade. A number of allegations as well as exculpation of different types are being held against it. The list of pros and cons of social networks is huge. India on one hand had an abundance of internet access in last half of the decade. The growth of social media and its influence on people have affected the society in both good as well as in bad way. The following research was done in the month of September and October. The research was carried out on 13 lakh tweets approximately, collected over the course of a month from September to October providing insights about the different attributes of general tweets available on Twitter API for analysis. Insights include the hashtags, account mentions, sentiment, polarity, subject, and object of a tweet. The topics like Rhea Chakraborty and Sushant Singh Rajput, PM Narendra Modi's Birthday, IPL 2020 overshadowed the topics like COVID-19 and women's security.

Analysis Report for Statistics in the Twitter Network

Twitter is the most popular social networking service across the world. In Twitter, the messages are known as tweets. Tweets are mainly text-based posts that can be up to 140 characters long which can reach the author's subscribers. These subscribers are also known as followers. Such subscriptions form a direct connection. But these connections are not always symmetric. In this study, the authors have assumed that if two nodes are connected, then the tweet is propagated between them without any other conditions. But using sentiment analysis, the general opinion of people about various things can be figured. The Twitter data set analyzed includes almost 20k nodes and 33k edges, where the visualization is done with software called Gephi. Later a deep dive analysis is done by calculating some of the metrics such as degree centrality and closeness centrality for the obtained Twitter network. Using this analysis, it is easy to find the influencers in the Twitter network and also the various groups involved in the network.

Information Retrieval in Business Industry Using Blockchain Technology and Artificial Intelligence

Industry 5.0 promotes automation in an optimized way. Collaboration with blockchain technology and artificial intelligence helps to enrich Industry 5.0 with its quantifiers and qualifiers. In the business industry, information plays an iconic role. When we consider the issues of storage and retrieval, we need to think about blockchain technology where the data will be stored and shared in a secure way. Here, the data will be distributed across the network in an encrypted format; hence, the original data can be viewed only by the owner of the data. Blockchain stores the information in the form of blocks. Every block has three sections. The first section holds the hash value of the previous block, the second one holds the information to be stored in a block, and the third one holds the hash value of an upcoming block. It does not allow an intruder to hack or modify the data without user's knowledge as these blocks are interconnected on both the sides with their hashes. This synergy of technologies brings supremacy in the field of business industries which will be discussed in this chapter.

Recent Trends in Deepfake Detection

Almost 59% of the world's population is on the internet, and in 2020, globally, there were more than 3.81 billion individual social network users. Eighty-six percent of the internet users were fooled to spread fake news. The advanced artificial intelligence (AI) algorithms can generate fake digital content that appears to be realistic. The generated content can deceive the users into believing it is real. These fabricated contents are termed deepfakes. The common category of deepfakes is video deepfakes. The deep learning techniques, such as auto-encoders and generative adversarial network (GAN), generate near realistic digital content. The content generated poses a serious threat to the multiple dimensions of human life and civil society. This chapter provides a comprehensive discussion on deepfake generation, detection techniques, deepfake generation tools, datasets, applications, and research trends.

Mathematical Information Retrieval Trends and Techniques

Mathematical formulas are widely used to express ideas and fundamental principles of science, technology, engineering, and mathematics. The rapidly growing research in science and engineering leads to a generation of a huge number of scientific documents which contain both textual as well as mathematical terms. In a scientific document, the sense of mathematical formulae is conveyed through the context and the symbolic structure which follows the strong domain specific conventions. In contrast to textual information, developed mathematical information retrieval systems have demonstrated the unique and elite indexing and matching approaches which are beneficial to the retrieval of formulae and scientific term. This chapter discusses the recent advancement in formula-based search engines, various formula representation styles and indexing techniques, benefits of formula-based search engines in various future applications like plagiarism detection, math recommendation system, etc.

Deep NLP in the Healthcare Industry

A reliable provocative issue which impacts the joints by harming the body's tissue is called rheumatoid arthritis. The ID of rheumatoid arthritis by hand, particularly during its unanticipated turn of events or pre-expressive stages, requires an extraordinary construction analysis. The standard end technique for rheumatoid arthritis (RA) calls for the assessment of hands and feet radiographs. Still, for clinical experts, it winds up being an unconventional endeavor considering the way that regularly the right completion of the disease relies on the exposure of unfathomably subtle changes for the typical eye. In this work, the authors built a design using convolutional neural networks (CNN) and reinforcement learning technique for detecting RA from hand and wrist MRI. For this, they took 564 cases (real information) which provided a precision of 100%. Compared to the existing system, the system showed a high performance with very good results. This model is highly recommended to detect rheumatoid arthritis automatically without human intervention.

Creditworthiness Assessment Using Natural Language Processing

NLP is a wide and quickly developing segment of today's new digital technology, which falls under the domain of artificial intelligence. Alternative approaches for qualifying and quantifying an individual's creditworthiness have emerged in recent years as a result of recent advancements in AI. Banks and creditors may use AI to rate potential borrowers' creditworthiness based on alternative data, such as social media messages and internet usage, such as which websites people visit and what they buy from e-commerce stores. These digital footprints may show whether or not an individual is able to repay their debts. In this chapter, how the approaches of NLP could offer financial solutions to unbanked communities is explored. This chapter includes the use of various machine learning algorithms and deep learning to find the most accurate credit score of a user. Since NLP is less intrusive than providing direct access to a person's entire contact list or a social media site, it is a more accessible way to measure risk while still having the potential to target a larger audience.

Language Processing and Python

Natural language processing is the communication between the humans and the computers. It is the field of computer science which incorporates artificial intelligence and linguistics where machine learning algorithms are used to analyze and process the enormous variety of data. This chapter delivers the fundamental concepts of language processing in Python such as text and word operations. It also gives the details about the preference of Python language for language processing and its advantages. It specifies the basic concept of variables, list, operators, looping statements in Python and explains how it can be implemented in language processing. It also specifies how a structured program can be written using Python, categorizing and tagging of words, how an information can be extracted from a text, syntactic and semantic analysis, and NLP applications. It also concentrates some of the research applications where NLP is applied and the challenges of NLP processing in the real-time area of applications.