What Is Information Retrieval and Why Does It Matter?”

Information Retrieval (IR) is a dynamic and essential process that focuses on the discovery and extraction of relevant information from vast collections of data in response to a user’s specific query. Originating from the fields of library science and computer science, IR has evolved into a crucial discipline in the digital age, where the volume of available information is expanding exponentially. At its core, IR aims to connect users with the exact data or resources they need, whether it involves text, multimedia, or other forms of information. The process typically involves indexing, organizing, and retrieving information from structured databases, semi-structured documents, or unstructured sources such as web pages and social media.

A significant aspect of IR lies in its ability to prioritize relevance. Modern IR systems use advanced techniques like natural language processing, machine learning, and algorithms to rank search results and present the most useful information to users. Applications of information retrieval span numerous fields, including search engines, digital libraries, academic databases, e-commerce platforms, and recommendation systems. For instance, search engines such as Google and Bing are powered by IR systems that analyze and filter massive amounts of web data to provide tailored results based on user input.

In today’s knowledge-driven society, the importance of effective information retrieval cannot be overstated. It serves as the backbone of efficient decision-making, research, and problem-solving. As technology advances, IR continues to integrate innovative tools like artificial intelligence to enhance the accuracy, speed, and personalization of information retrieval processes. By bridging the gap between users and the immense pool of data, IR systems empower individuals and organizations to navigate the complexities of information overload, making knowledge accessible and actionable.

What Is Information Retrieval?

Information Retrieval (IR) is the process of finding and retrieving relevant information from a vast collection of data resources in response to a specific query or need. It is a field that bridges the gap between users and the vast amounts of structured, semi-structured, or unstructured data available in various formats such as text, images, videos, or audio. The primary goal of information retrieval is to ensure that users can efficiently and effectively locate the information they need without sifting through irrelevant or unrelated content.

In an IR system, the process begins with indexing the available data to create a structured way to organize and access it. When a user inputs a query, the system analyzes it and compares it against the indexed data to retrieve the most relevant results. Techniques like ranking algorithms, natural language processing, and relevance feedback are employed to improve the accuracy and usability of these systems. Examples of IR applications include search engines like Google and Bing, library catalogs, academic databases, and e-commerce platforms that offer product search functionality.

Information retrieval has become increasingly important in today’s data-driven world, where the sheer volume of information can overwhelm users. By enabling efficient access to relevant knowledge, IR systems empower research, decision-making, education, and many other activities. As technology advances, the field of IR continues to evolve, incorporating innovations like artificial intelligence and machine learning to improve retrieval accuracy, personalize results, and adapt to user behavior.

The Primary Goals of Information Retrieval in Modern Information Systems

The primary goal of information retrieval (IR) in modern information systems is to efficiently and effectively connect users with relevant and accurate information that addresses their specific needs or queries. In an age where vast amounts of data are generated and stored across various platforms, IR systems aim to organize, index, and retrieve data to ensure quick and meaningful access, helping users navigate the overwhelming sea of information. This goal revolves around several key principles:

• Ensuring Relevance: The cornerstone of any IR system is relevance—retrieving information that directly aligns with the user’s query. When a user inputs a search, the system must interpret the query accurately and analyze the context to deliver results that satisfy the user’s intent. Relevance is achieved through advanced ranking algorithms, semantic analysis, and natural language processing (NLP), which together help prioritize results that are most likely to be useful to the user.
• Delivering Efficiency: In a world where speed is of the essence, efficiency is another critical goal of modern IR systems. Users expect to receive results almost instantaneously, regardless of the size or complexity of the underlying dataset. To meet this demand, IR systems rely on techniques like indexing, caching, and optimized search algorithms. The goal is to minimize latency while maximizing the system’s capacity to handle large-scale data queries.
• Achieving Accuracy: Beyond relevance and efficiency, accuracy is essential to ensuring that the information retrieved is correct and reliable. In fields like healthcare, legal research, and scientific studies, the quality of retrieved data can have profound implications. Accurate retrieval ensures that users can trust the information they receive, empowering them to make informed decisions and draw valid conclusions.
• Enhancing Accessibility: Modern IR systems aim to make information universally accessible, accommodating diverse users with varying needs. Accessibility involves designing user-friendly interfaces, supporting multiple languages, and providing assistive features for users with disabilities. Features like voice search, autocomplete, and intuitive filters also contribute to making IR systems more accessible and inclusive.
• Offering Personalization: Personalization has become a key focus in information retrieval. By analyzing user behavior, preferences, and past interactions, modern IR systems can tailor search results to individual users. Personalized retrieval improves user satisfaction and reduces the time and effort required to find relevant information. For example, e-commerce platforms often recommend products based on a user’s search history and preferences, streamlining the shopping experience.
• Ensuring Scalability: As the volume of data continues to grow exponentially, scalability has become a critical goal for IR systems. Whether handling structured data like databases or unstructured content like social media posts, IR systems must be able to scale without compromising efficiency or accuracy. This involves using distributed systems, cloud computing, and other technologies to manage and process data effectively.
• Combating Information Overload: In the era of information overload, where users are inundated with an abundance of data, IR systems must help filter out irrelevant content and focus on delivering concise, organized, and actionable results. Techniques like clustering, summarization, and semantic analysis enable IR systems to present results that are easier to navigate and more meaningful to the user.

The primary goals of information retrieval in modern information systems go far beyond simply fetching data. They encompass a range of objectives aimed at delivering a seamless, user-centric experience. By focusing on relevance, efficiency, accuracy, accessibility, personalization, scalability, and adaptability, IR systems empower users to navigate the complexities of today’s information-rich world with ease. Whether for academic research, professional decision-making, or everyday searches, information retrieval systems are an indispensable tool for unlocking the potential of the vast digital landscape.

The Fundamental Components of an Information Retrieval System

An information retrieval (IR) system is designed to organize, store, and retrieve relevant information in response to user queries. To achieve this, IR systems rely on several fundamental components that work together to ensure efficient and accurate retrieval of information. Here are the key components of an IR system:

1. Document Collection: At the core of any information retrieval system is the document collection, which represents the database or repository of resources from which the system retrieves information. These documents can vary in format, including text (e.g., books, articles, or web pages), images, videos, and audio files. The document collection may consist of structured data (organized in fields and records), semi-structured data (like XML or JSON files), or unstructured data (such as free text). The size and nature of the collection significantly impact the design and performance of the IR system.
2. Indexing Component: The indexing component is critical to the functionality of an IR system. It involves organizing the document collection into a structured representation, known as an index, which allows for faster and more efficient searching. The index is built by extracting key terms, phrases, and metadata from the documents and mapping them to their corresponding locations in the collection. Techniques such as inverted indexing—a method where terms are mapped to the documents in which they appear—are widely used. This component reduces the time needed to retrieve relevant documents and ensures scalability as the document collection grows.
3. Query Processor: The query processor is the interface that bridges user queries and the retrieval system. Its primary role is to interpret and process user input, ensuring the query is accurately matched with the indexed data. This component includes several functions:
   • Parsing the query to identify keywords and operators.
   • Normalizing the query through stemming (reducing words to their base forms) or removing stop words (e.g., “the,” “and”).
   • Expanding the query by incorporating synonyms or related terms to improve recall.
     By refining the user’s input, the query processor ensures the IR system can effectively understand and respond to the search intent.
4. Matching and Retrieval Component: The matching and retrieval component is the engine of the IR system, responsible for comparing user queries with the indexed data and identifying relevant documents. This component uses various retrieval models to determine how well a document matches a query. Common models include:
   • Boolean Retrieval Model: Matches documents based on Boolean operators like AND, OR, and NOT.
   • Vector Space Model (VSM): Represents documents and queries as vectors and calculates their similarity.
   • Probabilistic Models: Estimate the likelihood that a document is relevant to a query.
   • Machine Learning Models: Employ algorithms that learn from user behavior to improve retrieval accuracy.
     The retrieval process ensures that only the most relevant documents are presented to the user.
5. Ranking Component: Not all retrieved documents are equally relevant to a query, which is why the ranking component is essential. This component evaluates and orders the retrieved results based on their relevance to the user’s query. It uses scoring functions that take into account factors such as:
   • Term Frequency-Inverse Document Frequency (TF-IDF): A measure of how important a term is in a document relative to its rarity across the collection.
   • Semantic Relevance: The contextual meaning of the query terms in relation to the document.
   • Metadata: Attributes like publication date, author reputation, or popularity.
     Ranking ensures that users see the most relevant results first, improving their overall search experience.
6. User Interface: The user interface (UI) is the component that directly interacts with the user, enabling them to input queries and view search results. A well-designed UI is crucial for enhancing the usability and accessibility of the IR system. It typically includes:
   • A search bar for entering queries.
   • Result previews (e.g., snippets of text, thumbnails, or metadata).
   • Filters and sorting options (e.g., by date, relevance, or file type).
   • Advanced search features for complex queries.
     The UI serves as the bridge between the user and the underlying retrieval process, making it intuitive and straightforward to interact with the system.
7. Feedback Mechanism: Many modern IR systems include a feedback mechanism to refine search results and improve system performance over time. Feedback can be explicit, where users rate the relevance of results or provide input, or implicit, where the system observes user behavior (e.g., click patterns, time spent on a document). This feedback is used to adjust ranking algorithms, personalize results, and improve the overall retrieval process.
8. Evaluation Component: The evaluation component ensures the IR system performs effectively by measuring its success in retrieving relevant information. Common metrics include:
   • Precision: The proportion of relevant documents that were retrieved.
   • Recall: The proportion of relevant documents in the collection that are retrieved.
   • F1 Score: A harmonic mean of precision and recall.
   • Mean Average Precision (MAP): Assesses the ranking quality of results.
     These metrics help developers optimize the system to better meet user needs.
9. Storage and Database Management: Behind the scenes, the IR system relies on robust storage and database management to store the original documents, metadata, and indexes. Efficient data storage ensures the system can handle large collections and retrieve information without significant delays.

The fundamental components of an information retrieval system work together to provide a seamless and efficient search experience for users. Each component plays a vital role in the system’s overall functionality, from organizing the document collection to interpreting user queries, retrieving results, and refining relevance. In a world where data continues to grow exponentially, these components ensure that IR systems remain effective, scalable, and user-friendly, helping individuals and organizations navigate the ever-expanding landscape of information.

How Do Search Engines Utilize Information Retrieval Principles to Provide Relevant Results?

Search engines rely on key information retrieval (IR) principles to provide relevant results to users by efficiently organizing, processing, and ranking vast amounts of data. The process begins with crawling, where search engines use automated programs called crawlers or spiders to browse the web and gather data from websites. This data is then indexed, where the search engine creates an inverted index that maps keywords to their locations in the documents, enabling quick retrieval of information. When a user submits a query, the search engine’s query processor interprets the input, breaking it down into search terms, normalizing them (removing stop words and applying stemming or lemmatization), and expanding the query if necessary to improve search results.

Once the query is processed, the search engine uses various matching and retrieval models to find documents that contain the query terms. Common models include the Boolean model, which applies logical operators like AND, OR, and NOT, and the vector space model, which represents both documents and queries as vectors and calculates their similarity. After identifying relevant documents, the ranking algorithm ranks the results based on factors like term frequency-inverse document frequency (TF-IDF), which evaluates how important a term is in a document, and PageRank, which uses the quantity and quality of links to determine a document’s authority and relevance.

Furthermore, search engines increasingly incorporate personalization, adjusting results based on a user’s search history, location, or preferences to provide more tailored answers. Natural Language Processing (NLP) also plays a significant role, helping search engines understand the context and meaning of complex or conversational queries beyond simple keyword matching. Finally, search engines utilize feedback mechanisms, such as user clicks and time spent on pages, to continuously improve their algorithms, adjusting rankings and refining the relevance of results over time. By combining these IR principles—crawling, indexing, query processing, ranking, personalization, NLP, and feedback—search engines can deliver highly relevant and timely results, ensuring that users find the information they are seeking efficiently and effectively.

What Is the Role of Indexing in the Information Retrieval Process?

Indexing plays a pivotal role in the information retrieval (IR) process by enabling the system to quickly locate and retrieve relevant documents from vast collections of data. Without indexing, an IR system would have to scan the entire document collection every time a query is made, which would be time-consuming and inefficient. Instead, indexing organizes the data in a structured format, allowing for faster searching. One of the most common indexing methods is the inverted index, where each keyword or term in the document collection is mapped to the list of documents in which it appears, along with the term’s position within the document. This structure allows the system to quickly identify which documents contain the queried terms and retrieve them efficiently.

Beyond speed, indexing also enhances relevance ranking by enabling the IR system to assess which documents are most pertinent to the user’s query. For example, documents, where the query term appears more frequently or in important locations (such as the title or heading), are likely to be ranked higher. Additionally, indexing supports advanced search features, such as phrase search and wildcard search, which are essential for users to conduct more flexible and precise queries. Indexing not just the terms but also other document attributes like metadata enables more complex searches, such as filtering by author, date, or document type.

Moreover, indexing is crucial for handling large datasets efficiently. As the amount of digital content grows, indexing allows systems to manage and retrieve data at scale, avoiding the need for slow, linear searches. Full-text indexing, in which the entire content of a document is indexed, ensures that users can search for specific terms anywhere within a document rather than being restricted to titles or abstracts. In sum, indexing makes the entire information retrieval process faster, more accurate, and more capable of handling complex queries, ensuring that users can access the information they need with minimal delay.

Key Applications of Information Retrieval in Everyday Life

Information retrieval (IR) plays a significant role in many aspects of everyday life, helping individuals and organizations quickly access relevant information from vast amounts of data. Here are some key applications of IR in daily life:

1. Search Engines: The most obvious and widely used application of IR is in search engines like Google, Bing, and Yahoo. When a user types a query into a search engine, the system quickly retrieves a list of web pages, images, videos, and other resources that best match the user’s search terms. Search engines rely heavily on indexing, ranking algorithms, and relevance scoring to ensure that the most pertinent results are presented at the top. The ability to instantly access information on almost any topic has become a staple of modern life, and search engines have made it easier than ever to find answers, learn new things, and explore the digital world.
2. Online Shopping: In e-commerce platforms like Amazon, eBay, and Etsy, information retrieval helps users quickly find products that match their search criteria. When a user searches for a product, the IR system indexes the product descriptions, reviews, and metadata to return the most relevant results. By analyzing factors like keywords, prices, and user ratings, IR ensures customers are presented with the best options. Additionally, IR techniques power recommendation systems that suggest products based on a user’s past behavior, preferences, and browsing history, helping to personalize the shopping experience.
3. Social Media: Social media platforms, such as Facebook, Instagram, Twitter, and LinkedIn, use IR to organize and surface relevant content for users. When users search for hashtags, profiles, or posts, the system retrieves relevant results from vast datasets, ranking them based on factors such as popularity, engagement, and user interests. The IR systems also index content such as photos, videos, and comments to help users discover new posts and people to follow. Furthermore, personalized content feeds are curated using IR principles, tailoring what users see based on their past interactions, likes, and networks.
4. Voice Assistants: Voice-activated assistants like Siri, Google Assistant, and Amazon Alexa utilize information retrieval to respond to user queries. These systems interpret natural language, process the input, and retrieve relevant answers or perform tasks by searching indexed data sources. Whether you’re asking for the weather, setting reminders, or controlling smart devices in your home, voice assistants rely on IR techniques to understand your request and deliver the most relevant results. As these systems continue to improve, they are becoming increasingly adept at understanding complex queries and providing highly personalized responses.
5. Navigation and Maps: Applications like Google Maps and Apple Maps rely on IR to provide users with the most relevant directions, routes, and location-based information. These apps index geographic data, points of interest, and user reviews to help users find businesses, landmarks, restaurants, and other places of interest. When you search for “best pizza near me” or ask for directions to a destination, the app uses IR techniques to match your query with the most relevant and accurate locations. Additionally, real-time traffic data and route optimization are powered by advanced IR systems that help ensure the fastest and most efficient travel.
6. News and Content Aggregators: News apps like Google News and content aggregation platforms such as Flipboard and Pocket use information retrieval systems to curate personalized news feeds for users. By indexing articles, blog posts, and media content, these platforms can offer relevant news updates based on users’ reading habits, interests, and previous interactions. IR algorithms sort through vast amounts of content to prioritize stories that match the user’s preferences, ensuring that they are always up to date on the topics that matter most.
7. Customer Support and FAQs: In customer service, many companies use information retrieval systems to power chatbots and customer support portals. These systems index frequently asked questions (FAQs), support documents, and past customer interactions to provide immediate responses to common inquiries. For more complex issues, IR-powered systems can help direct customers to the appropriate human representative by matching keywords or phrases from their queries with relevant support topics. This use of IR helps streamline customer service operations, ensuring faster and more accurate resolutions for customers.
8. Streaming Services: Streaming platforms like Netflix, Spotify, and YouTube rely on IR to recommend personalized content to users. Whether you’re searching for a movie, song, or video, the IR system indexes content by genre, title, rating, and user preferences to surface the most relevant results. Additionally, the platforms use IR techniques to suggest new content based on your past viewing or listening habits. By analyzing user behavior, IR systems ensure that recommendations become increasingly tailored to individual tastes, improving the overall user experience and helping users discover new content that matches their interests.
9. Job Search Engines: In job search portals like LinkedIn, Indeed, and Glassdoor, IR systems help users find the most relevant job opportunities. When users search for positions based on keywords such as job titles, skills, and location, the IR system indexes and ranks job listings accordingly. By analyzing factors like experience level, location, and company size, the system ensures that users are presented with jobs that best fit their qualifications and preferences. Additionally, some platforms use IR to recommend job opportunities based on users’ profiles and past job searches.
10. Healthcare and Medical Search: Healthcare professionals and patients use IR-powered tools to search for relevant medical information. Platforms like PubMed, UpToDate, and WebMD use information retrieval to index and retrieve research papers, medical articles, symptoms, treatments, and drug information. These systems help healthcare professionals stay informed about the latest medical advances and assist patients in finding reliable health information. By organizing vast amounts of medical data, IR systems enable quick access to critical health-related resources.

Information retrieval has become an integral part of everyday life, providing users with fast and accurate access to the information they need, whether they’re conducting a web search, shopping online, navigating a city, or streaming content. From search engines and social media platforms to voice assistants and job portals, IR is behind the scenes in many of the tools we use daily. By indexing, organizing, and ranking vast amounts of data, information retrieval systems help ensure that users find the most relevant and timely results, making the digital world more accessible and navigable than ever before.

How Has the Advancement of Artificial Intelligence Enhanced Information Retrieval Systems?

The advancement of artificial intelligence (AI) has significantly enhanced information retrieval (IR) systems by making them more efficient, accurate, and user-friendly. Traditional IR systems mainly relied on simple keyword matching and indexing techniques, but AI has brought new capabilities that allow systems to understand complex queries, improve relevance, and continuously adapt to user preferences. Natural language processing (NLP) has played a crucial role in this evolution, allowing systems to understand and process queries in natural language. AI-powered NLP enables IR systems to interpret the meaning behind words, recognize synonyms, and handle variations in language, which leads to more accurate and context-aware search results.

Another major advancement is the shift from basic keyword search to semantic search. AI helps systems understand the context of a query, not just the specific words, allowing for more relevant results. For example, a user searching for “best way to reduce stress” might receive results on mental health practices, even if the exact words don’t match. AI techniques such as word embeddings and transformer models (like BERT and GPT) allow IR systems to interpret relationships between words and improve search accuracy.

AI has also enabled personalized search experiences, where IR systems tailor results based on user behavior, preferences, and past interactions. By analyzing patterns in user searches, clicks, and time spent on pages, AI systems can refine search results to match individual interests, reducing irrelevant results and enhancing user satisfaction. Furthermore, machine learning (ML) allows IR systems to continuously improve by learning from user interactions and adjusting algorithms based on feedback. This makes IR systems smarter over time, ensuring that they consistently provide more accurate and relevant results.

The integration of AI also revolutionized multimedia search. Traditional IR systems were limited to metadata or text-based searches, but AI techniques like computer vision and deep learning enable IR systems to analyze and understand images and videos. This allows users to search for visual content based on the objects, faces, or scenes depicted in images and videos, making multimedia search more precise and effective. Additionally, AI has enhanced voice search, making it possible for users to interact with systems using natural speech, further improving accessibility and convenience.

Information Retrieval: An Essential Pillar of Modern Information Systems

Information Retrieval (IR) has become an essential pillar of modern information systems, playing a critical role in how we access, manage, and utilize vast amounts of digital data. In today’s world, where information is being generated at an exponential rate, the need for effective and efficient systems that can help users quickly locate relevant information is more important than ever. IR is the process by which information systems search through large datasets—ranging from academic research papers to multimedia content—and retrieve the most relevant documents or data based on a user’s query. It is the foundation of modern search engines, digital libraries, e-commerce platforms, and social media sites, where its core goal is to make information accessible, accurate, and actionable for users.

The significance of IR lies in its ability to organize and index data in a way that makes it searchable and retrievable at scale. Traditional methods of finding information, such as manually browsing through physical archives, are no longer feasible, given the overwhelming volume of data generated daily. With advanced indexing techniques, IR systems can catalog and structure data in a way that allows for fast and efficient retrieval. This organization enables users to access the most pertinent information with minimal effort, ensuring that they can quickly find what they need amidst the sea of digital content available.

Beyond simple retrieval, modern IR systems also focus on improving the relevance of the search results. Through sophisticated algorithms and ranking methods, such as TF-IDF (Term Frequency-Inverse Document Frequency), PageRank, and machine learning models, IR systems can prioritize content that is most relevant to a user’s query. This is particularly important in contexts like search engines or digital libraries, where the quality of results can impact the user’s experience and decision-making. Relevance ranking ensures that users don’t just get any information—they receive the most accurate, valuable, and useful data available.

Another crucial aspect of IR systems is their ability to adapt and improve over time. With the integration of artificial intelligence (AI) and machine learning (ML), IR systems can personalize results based on user behavior, preferences, and historical interactions. For example, e-commerce platforms like Amazon or streaming services like Netflix utilize IR techniques to recommend products or content based on past searches, purchases, and ratings. AI also allows IR systems to better understand natural language, enabling users to ask complex questions in a conversational tone and receive meaningful results. This personalization and continuous learning make modern IR systems smarter, more intuitive, and increasingly aligned with individual user needs. Furthermore, the rise of multimedia content—such as images, videos, and audio—has led to innovations in IR techniques for non-textual data. Systems are now being developed to search and retrieve visual and auditory content based on context and content recognition rather than relying solely on metadata or descriptions. Techniques such as computer vision and speech recognition are revolutionizing how we search for and access multimedia, making it possible to find relevant content based on its visual features or spoken words.

In conclusion, information retrieval is undeniably an essential pillar of modern information systems. It enables us to efficiently access vast repositories of knowledge, ensuring that users can find the information they need quickly and accurately. From search engines and academic databases to e-commerce sites and multimedia platforms, IR systems are deeply embedded in our daily lives, shaping the way we interact with data. As technology continues to evolve, the role of IR will only grow more significant, powered by AI and machine learning, further enhancing the accuracy, speed, and relevance of search results in an increasingly data-driven world.

---

Acknowledgement:

1. Belkin, N. J. (2008). Some(what) grand challenges for information retrieval. SIGIR Forum, 42(1), 47–54. https://doi.org/10.1145/1394251.1394261
2. Ceri, S., Bozzon, A., Brambilla, M., Della Valle, E., Fraternali, P., & Quarteroni, S. (2013). An Introduction to Information Retrieval. In S. Ceri, A. Bozzon, M. Brambilla, E. Della Valle, P. Fraternali, & S. Quarteroni (Eds.), Web Information Retrieval (pp. 3–11). Springer. https://doi.org/10.1007/978-3-642-39314-3_1
3. Chowdhury, G. G. (2010). Introduction to Modern Information Retrieval. Facet Publishing.
4. Croft, W. B., Metzler, D., & Strohman, T. (n.d.). Search Engines Information Retrieval in Practice.
5. Goker, A., & Davies, J. (2009). Information Retrieval: Searching in the 21st Century. John Wiley & Sons.
6. Gudivada, V. N., Rao, D. L., & Gudivada, A. R. (2018). Chapter 11 – Information Retrieval: Concepts, Models, and Systems. In V. N. Gudivada & C. R. Rao (Eds.), Handbook of Statistics (Vol. 38, pp. 331–401). Elsevier. https://doi.org/10.1016/bs.host.2018.07.009
7. Hjørland, B. (2021). Information Retrieval and Knowledge Organization: A Perspective from the Philosophy of Science. Information, 12(3), Article 3. https://doi.org/10.3390/info12030135
8. Kowalski, G. J. (2007). Information Retrieval Systems: Theory and Implementation. Springer.
9. Manning, C. D., Raghavan, P., & Schütze, H. (2009). Introduction to Information Retrieval.
10. Melucci, M. (2015). Introduction to Information Retrieval and Quantum Mechanics (Vol. 35). Springer. https://doi.org/10.1007/978-3-662-48313-8
11. Mitra, B., & Craswell, N. (2018). An Introduction to Neural Information Retrieval. Foundations and Trends® in Information Retrieval, 13(1), 1–126. https://doi.org/10.1561/1500000061
12. Umeozor, S. N. (2020). Information Retrieval: A Communication Process in the 21st Century Library. International Journal of Knowledge Content Development & Technology, 10(2), 7–18. https://doi.org/10.5865/IJKCT.2020.10.2.007