A TECHNICAL SEMINAR REPORT

on
Bigdata Analytics
Submitted By
SUPRIYA PATHAPATI
Register Number: - 221FJ01056

In partial fulfilment of the requirements for the award of the degree of

BACHELOR OF TECHNOLOGY
in
INFORMATION TECHNOLOGY

VIGNAN’S FOUNDATION FOR SCIENCE, TECHNOLOGY AND RESEARCH

Deemed To Be University
+
(Accredited by NAAC “A ” grade)
Vadlamudi, Guntur – 522213
Andhra Pradesh

April-2024
 BONAFIDE CERTIFICATE

This is to certify that this Technical Seminar report “Unveiling the Digital Tapestry: Exploring the
Depths of Web Mining for Insight and Innovation” is the bonafide work of SARIKA GOLLA,
Register Number: - 221FJ01022 Department of Information Technology, Vignan’s Foundation for
Science, Technology and Research, Deemed to be University, for the award of degree of Bachelor of
Information Technology , who carried out the seminar work under my supervision.

Mr.P.Ramadoss & Mr. S.Nyamathulla Dr.N.Veeranjaneyalu

Coordinators - Technical Seminar, Head, Department of IT & CA
Associate Professor, Department of IT, VFSTR Deemed to be University
VFSTR Deemed to be University.

Internal / External Examiner

 ACKNOWLEDGEMENT

I am very grateful to our beloved Chairman Dr. Lavu Rathaiah, and Vice Chairman, Mr. Lavu Krishna
Devarayalu, for their love and care.

It is my pleasure to extend our sincere thanks to Vice-Chancellor Dr. P. Nagabhushan for providing an
opportunity to do my academics in Vignan’s Foundation for Science, Technology and Research
Deemed to be University.

I express my sincere thanks to Prof. Dr. N. Veeranjaneyalu, Head of the Department, Department of
Information Technology and Computer Application, Vignan’s Foundation for Science, Technology and
Research Deemed to be University, for his help and suggestion in carrying out this work.

It is a great pleasure for me to express my sincere thanks to Mr.P. Ramadoss & Mr. S.Nyamathulla
Assistant Professor, Department of Information Technology and Computer Application, VFSTR, for
their caring, advices and encouragement that helped me tread my path in this journey and achieve this
completed form.

I extend my whole-hearted gratitude to all my faculty members of Department of Information

Technology who helped us in our academics throughout course.

Finally I wish to express thanks to my family members for the love and affection overseas and
forbearance and cheerful depositions, which are vital for sustaining effort, required for completing this
work.

With Sincere regards,

By
SUPRIYA PATHAPATI(221FJ01056)
 TABLE OF CONTENTS

PAGE
Chapter no. TITLE
NO.

Abstract 5

List of Table

List of Figures 2

1. Introduction 6

2. Literature Review 7

3. Types of Web Mining 8

4. Web Content Mining 9

5. Web Structure Mining 10&11

6. Web Usage Mining 12&13

7. Applications of Web Mining 14&15

8. Challenges and Future Trends 16

9. Conclusion 17
 ABSTRACT

In today's digital era, the World Wide Web serves as a vast repository of information,

encompassing diverse content and structures. Web mining, a multidisciplinary field at the intersection

of information retrieval, data mining, and artificial intelligence, has emerged as a crucial tool for

extracting valuable insights and knowledge from the web. This paper presents a comprehensive

overview of web mining, covering its fundamental principles, methodologies, applications, and future

directions.The exploration begins with an elucidation of the three main types of web mining: web

content mining, web structure mining, and web usage mining. Web content mining focuses on

extracting valuable information from web pages, while web structure mining analyzes the linkages

between web pages. On the other hand, web usage mining delves into patterns of user interactions with

web resources, facilitating personalized recommendations and improved user experiences.

Throughout the discourse, various techniques and algorithms employed in each type of web

mining are elucidated, alongside their practical applications in domains such as e-commerce, social

media analysis, and information retrieval. Additionally, the paper addresses the inherent challenges and

ethical considerations associated with web mining, emphasizing the need for responsible data usage and

privacy protection.

Furthermore, the document discusses emerging trends and future directions in web mining,

including advancements in machine learning, deep learning, and big data analytics. The proliferation of

web mining tools and technologies is also highlighted, empowering researchers and practitioners to

harness the full potential of web data for societal benefit.

 CHAPTER 1
INTRODUCTION

In the digital age, the World Wide Web stands as an unparalleled repository of information,
encompassing a diverse array of content, structures, and interactions. With the exponential growth of
online data, the ability to extract valuable insights and knowledge from this vast expanse has become
increasingly vital. This imperative has catalyzed the emergence of web mining, a multidisciplinary field
that blends techniques from information retrieval, data mining, and artificial intelligence to uncover
hidden patterns, trends, and knowledge embedded within web data.

Web mining, at its core, represents a powerful mechanism for turning raw web data into actionable
intelligence. By employing sophisticated algorithms and methodologies, web mining enables the
discovery of meaningful patterns in web content, the analysis of complex linkages between web pages,
and the interpretation of user interactions with web resources. Through this process, organizations and
individuals can gain profound insights into user behavior, market trends, and emerging phenomena,
thereby informing strategic decision-making, enhancing user experiences, and driving innovation.

The significance of web mining extends across a multitude of domains, ranging from e-commerce and
digital marketing to healthcare, social media analysis, and beyond. In e-commerce, for instance, web
mining facilitates personalized product recommendations, targeted advertising, and market
segmentation based on customer preferences. In healthcare, it enables the analysis of online health
forums to identify emerging health trends and facilitate proactive interventions. Similarly, in social
media analysis, web mining techniques empower researchers to analyze sentiment, detect fake news,
and understand social network dynamics.

However, the practice of web mining is not without its challenges and ethical considerations. As the
volume and complexity of web data continue to grow, issues such as data privacy, information
overload, and algorithmic bias loom large. Responsible and ethical use of web mining techniques is
imperative to safeguard user privacy, ensure data integrity, and mitigate potential societal harms.

Despite these challenges, the field of web mining is poised for continued growth and innovation.
Advancements in machine learning, natural language processing, and big data analytics promise to
unlock new capabilities and insights from web data. Moreover, the proliferation of web mining tools
and technologies democratizes access to web mining capabilities, enabling researchers, businesses, and
individuals to harness the power of web data for diverse applications.

In this paper, we embark on a journey into the realm of web mining, exploring its fundamental
principles, methodologies, applications, and future directions. Through a comprehensive examination
of web mining techniques, case studies, and emerging trends, we aim to provide readers with a deeper
understanding of this dynamic field and its transformative potential in the digital age.
 CHAPTER 2

LITERATURE REVIEW:

The literature on web mining encompasses a diverse array of studies that collectively provide insights
into the extraction of valuable information from the World Wide Web. Previous works have explored
various aspects of web mining, including foundational studies, types of web mining, applications across
different domains, challenges, and future directions.

Foundational studies in web mining have laid the groundwork for subsequent research endeavors.
Researchers such as S. Chakrabarti et al. (1999) have delved into the concept of focused crawling,
proposing algorithms for efficiently navigating the web to gather relevant content. Similarly, R. Cooley
et al. (1997) pioneered the field of web usage mining, exploring techniques for analyzing user
interactions with web resources to uncover usage patterns and trends.

The exploration of different types of web mining has been a focal point of research efforts. Scholars
have investigated web content mining techniques such as text mining, multimedia mining, and
sentiment analysis. Additionally, web structure mining, involving the analysis of linkages between web
pages using graph-based algorithms and link analysis techniques, has garnered significant attention.
Moreover, web usage mining, which focuses on analyzing user interactions with web resources, has
been extensively studied, particularly in the context of personalized recommendation systems and user
behavior analysis.

Applications of web mining span a wide range of domains, including e-commerce, healthcare, social
media analysis, and information retrieval. Previous studies have demonstrated the utility of web mining
techniques in personalized product recommendations, market basket analysis, disease outbreak
detection, sentiment analysis, and fake news detection.

Despite its promise, web mining is not without its challenges and ethical considerations. Issues such as
data privacy, information overload, and algorithmic bias have been identified as significant hurdles to
the responsible and ethical use of web mining techniques. Scholars emphasize the importance of
transparency, accountability, and fairness in web mining practices to mitigate potential societal harms.

Looking ahead, the field of web mining is poised for continued growth and innovation. Advancements
in machine learning, deep learning, and big data analytics are expected to unlock new capabilities and
insights from web data. Moreover, the democratization of web mining tools and technologies
empowers researchers, businesses, and individuals to harness the power of web data for diverse
applications.

In summary, the literature on web mining provides a rich tapestry of studies exploring various facets of
information extraction from the World Wide Web. Previous works have contributed to our
understanding of foundational principles, methodologies, applications, challenges, and future directions
in the field of web mining.
 CHAPTER 3

Types of Web Mining

web mining encompasses three main types:1.web content mining 2.web structure mining, and web
usage mining each offering valuable insights and applications in various domains. These techniques
play a crucial role in extracting knowledge from the vast expanse of the World Wide Web, empowering
organizations to make informed decisions and provide personalized experiences to users.
1. Web Content Mining:
Web content mining focuses on extracting valuable information from web pages. It involves techniques
for retrieving, processing, and analyzing the textual, visual, and multimedia content available on the
World Wide Web. Several techniques are employed in web content mining:
2. Web Structure Mining:
Web structure mining involves analyzing the linkages between web pages to uncover patterns and
relationships within the underlying structure of the World Wide Web. Techniques employed in web
structure mining include:
3. Web Usage Mining:
Web usage mining involves analyzing user interactions with web resources to understand user
behavior, preferences, and patterns. Techniques employed in web usage mining include:
 CHAPTER 4

WEB CONTENT MINING

1. Web Crawling:
Web crawling, also known as web scraping or web harvesting, is the process of systematically
browsing the web to gather information from web pages. Search engines use web crawlers to index the
content of web pages, enabling users to retrieve relevant information through search queries. Web
crawlers traverse the web by following hyperlinks from one web page to another, recursively
discovering and fetching web pages. Techniques such as breadth-first or depth-first crawling are
employed to efficiently navigate the web and collect data for further analysis.

2. Text Mining:
Text mining involves extracting structured information from unstructured text data available on web
pages. Techniques used in text mining include:

Natural Language Processing (NLP): NLP techniques are used to analyze and understand human
language text. This includes tasks such as tokenization, part-of-speech tagging, named entity
recognition, and sentiment analysis. NLP enables the extraction of meaningful information from text,
such as identifying key phrases, entities, and sentiments expressed in web documents.

Information Extraction: Information extraction techniques focus on identifying and extracting specific
types of information from text, such as entities, relationships, and events. This includes techniques such
as named entity recognition, entity linking, and relation extraction. Information extraction enables the
extraction of structured data from unstructured text, facilitating further analysis and interpretation.

3. Multimedia Mining:
Multimedia mining extends the scope of content mining to include non-textual data such as images,
videos, and audio files available on web pages. Techniques used in multimedia mining include:

Image Recognition: Image recognition techniques involve analyzing and interpreting visual content
within images. This includes tasks such as object detection, image classification, and image
segmentation. Image recognition enables the extraction of information from images, such as identifying
objects, scenes, and patterns depicted in web images.

Video Analysis: Video analysis techniques focus on extracting information from video content, such as
identifying objects, actions, and events depicted in videos. This includes tasks such as video
summarization, action recognition, and object tracking. Video analysis enables the extraction of
meaningful insights from web videos, facilitating tasks such as content recommendation and video
search.

How Content Mining Extracts Valuable Information from Web Pages:

Content mining extracts valuable information from web pages by systematically analyzing the textual,
visual, and multimedia content available on the web. By employing techniques such as web crawling,
text mining, and multimedia mining, content mining enables the extraction of structured data, key
insights, and knowledge from unstructured web content. This extracted information can be used for
various purposes, such as information retrieval, knowledge discovery, sentiment analysis,
recommendation systems, and decision-making in diverse domains such as e-commerce, healthcare,
social media, and more. Overall, content mining plays a crucial role in unlocking the wealth of
information stored within the vast expanse of the World Wide Web, empowering individuals and
organizations to make informed decisions and derive value from web data.

CHAPTER 5
 Web Structure Mining

Web structure mining focuses on analyzing the linkages between web pages to uncover patterns and relationships
within the underlying structure of the World Wide Web. This involves understanding the topology of the web graph,
which consists of interconnected nodes representing web pages and edges representing hyperlinks between them.
Techniques such as link analysis and graph mining are employed to analyze the structure of the web graph and
extract valuable insights.

1. Link Analysis:

Link analysis is a fundamental technique in web structure mining that involves examining the network of hyperlinks
between web pages. This technique is based on the premise that the structure of the web graph can provide valuable
information about the importance, authority, and relevance of web pages. Some key concepts in link analysis
include:

PageRank: PageRank is a link analysis algorithm developed by Larry Page and Sergey Brin, the founders of Google.
It assigns a numerical score to each web page based on the number and quality of inbound links it receives from
other pages. Pages with a higher PageRank score are considered more authoritative and relevant, influencing their
ranking in search engine results.

HITS (Hyperlink-Induced Topic Search): HITS is another link analysis algorithm that evaluates the quality of web
pages based on their authority and hub scores. Authority pages are those that are highly cited and contain valuable
content, while hub pages are those that link to authoritative pages. HITS identifies authoritative pages by iteratively
computing authority and hub scores based on the link structure of the web graph.

2. Graph Mining:

Graph mining techniques extend the analysis of web structure beyond individual web pages to explore patterns and
relationships within the web graph as a whole. This involves applying algorithms and methods from graph theory to
analyze the topology, connectivity, and properties of the web graph. Some key concepts in graph mining include:

Community Detection: Community detection techniques identify clusters or communities of closely connected web
pages within the web graph. These communities represent groups of pages that share similar topics, themes, or
interests. Community detection algorithms help uncover hidden structures and patterns within the web graph,
facilitating tasks such as content recommendation, topic modeling, and trend detection.

Anomaly Detection: Anomaly detection techniques identify unusual or anomalous patterns within the web graph
that deviate from the expected behavior. This includes detecting spam links, link farms, and other forms of web
manipulation that attempt to manipulate search engine rankings. Anomaly detection algorithms help maintain the
integrity and quality of search engine results by identifying and penalizing suspicious behavior.
How Structure Mining Analyzes the Linkages Between Web Pages:

Structure mining analyzes the linkages between web pages by examining the topology of the web graph and
extracting patterns, relationships, and properties inherent in the link structure. Techniques such as link analysis and
graph mining enable researchers and practitioners to gain insights into the authority, relevance, and connectivity of
web pages within the web graph. By understanding the underlying structure of the web, structure mining helps
improve search engine algorithms, identify authoritative sources, detect anomalies, and enhance the overall quality
of search results and web navigation experiences. Overall, structure mining plays a crucial role in uncovering
valuable insights from the vast interconnected network of web pages on the World Wide Web.
 CHAPTER 6

Web Usage Mining

Web usage mining focuses on analyzing user interactions with web resources to understand user
behavior, preferences, and patterns. It involves techniques such as sessionization, pattern discovery,
and recommendation systems, each contributing to the extraction of valuable insights from user
activity on the World Wide Web.

1. Sessionization:
Sessionization is the process of segmenting user interactions into sessions based on temporal
and navigational criteria. A session represents a period of continuous activity by a user on a website,
typically characterized by a sequence of page views, clicks, and other interactions. Techniques for
sessionization include:

Time-based Sessionization: Sessions are defined based on time intervals, with a new session starting
after a specified period of inactivity (e.g., 30 minutes).

Page-view-based Sessionization: Sessions are defined based on a sequence of page views, with a new
session starting when a user navigates to a new page or closes the browser.

Sessionization enables analysts to group related user actions and study user behavior within individual
sessions, facilitating tasks such as behavior analysis, session-based recommendation, and website
optimization.

2. Pattern Discovery:
Pattern discovery techniques aim to identify recurring patterns, sequences, and associations
within user interactions with web resources. This involves analyzing clickstream data, navigation
paths, and other user behavior data to uncover meaningful insights. Techniques for pattern discovery
include:

Sequential Pattern Mining: Sequential pattern mining algorithms identify patterns of user
behavior that occur in a specific sequence or order. This includes tasks such as identifying frequently
occurring navigation paths, clickstream patterns, and session sequences.

Association Rule Mining: Association rule mining techniques identify relationships and
associations between different elements of user behavior. This includes tasks such as identifying
frequently co-occurring pages, items, or actions within user sessions.

Pattern discovery enables analysts to uncover hidden relationships, preferences, and trends
within user interactions, facilitating tasks such as personalized recommendation, content optimization,
and marketing strategy development.

3. Recommendation Systems:

Recommendation systems leverage user behavior data to provide personalized

recommendations for products, services, and content. Techniques for recommendation systems
include:
Collaborative Filtering: Collaborative filtering techniques analyze user behavior data to identify
similarities between users and items. This includes methods such as user-based and item-based
collaborative filtering, which recommend items based on the preferences of similar users or items.
Content-based Filtering: Content-based filtering techniques analyze the attributes and features of
items to generate recommendations based on user preferences. This includes methods such as text
analysis, image analysis, and feature extraction to recommend items similar to those previously
interacted with by the user.

Recommendation systems enable websites and applications to deliver personalized experiences,

improve user engagement, and increase user satisfaction by suggesting relevant content, products, and
services based on past user behavior.

How Usage Mining Extracts Patterns from User Interactions with Web Resources:

Usage mining extracts patterns from user interactions with web resources by analyzing clickstream
data, navigation paths, and other user behavior data collected during website visits. Techniques such
as sessionization segment user interactions into meaningful sessions, while pattern discovery
techniques identify recurring patterns, sequences, and associations within user behavior.
Recommendation systems leverage user behavior data to provide personalized recommendations for
products, services, and content based on past user interactions.

By analyzing user behavior data, usage mining enables organizations to gain insights into user
preferences, behavior trends, and engagement patterns, facilitating tasks such as website optimization,
content personalization, and marketing strategy development. Overall, usage mining plays a crucial
role in understanding and improving the user experience on the World Wide Web.
 CHAPTER 7
APPLICATIONS OF WEB MINING

Here are some real-world applications of web mining in different domains:

E-commerce:
Market Basket Analysis: Retailers use web mining techniques to analyze customer purchase patterns
and identify associations between products. For example, if a customer buys diapers, they might also
purchase baby wipes and formula.
Personalized Recommendation Systems: E-commerce platforms like Amazon use web mining to
recommend products based on a user's browsing and purchase history. For instance, Netflix suggests
movies and TV shows based on a user's viewing habits.
Customer Segmentation: Web mining helps businesses segment their customer base based on
demographic and behavioral data. For instance, a clothing retailer might target different marketing
campaigns to young adults and seniors based on their browsing history.
Social Media Analysis:
Sentiment Analysis: Companies use web mining to analyze social media conversations and gauge
public sentiment towards their brand or products. For example, Twitter sentiment analysis can help
companies understand how customers feel about their latest product launch.
Trend Detection: Web mining helps identify emerging trends and topics of discussion on social media
platforms. For instance, businesses can use web mining to identify trending hashtags and capitalize on
popular topics in their marketing campaigns.
Influencer Identification: Web mining techniques help identify influential users on social media who
can help amplify a brand's message. For example, companies may partner with social media
influencers to promote their products to a larger audience.
Information Retrieval:
Web Search Engines: Search engines like Google use web mining algorithms to index and rank web
pages based on their relevance to a user's query. For example, Google's PageRank algorithm analyzes
the link structure of the web to determine the authority and importance of web pages.
Content Summarization: Web mining techniques can be used to automatically summarize web
content, making it easier for users to digest large amounts of information quickly. For example, news
aggregation websites often use web mining algorithms to generate article summaries.
Case Studies:
Amazon's Recommendation System: Amazon's recommendation system, powered by web mining
techniques, is estimated to contribute to 35% of the company's revenue. By analyzing user browsing
and purchase history, Amazon can recommend relevant products to users, leading to increased sales
and customer satisfaction.
Twitter Sentiment Analysis: During the 2020 U.S. presidential election, Twitter sentiment analysis
played a crucial role in gauging public opinion and predicting election outcomes. Analysts used web
mining techniques to analyze millions of tweets and assess voter sentiment towards different
candidates and issues.

These examples illustrate the effectiveness of web mining in various domains, showcasing its ability
to extract valuable insights from web data and drive decision-making in real-world scenarios.
 CHAPTER 8
CHALLENGES AND FUTURE TRENDS
Challenges in Web Mining:
Data Privacy: One of the significant challenges in web mining is ensuring data privacy and protection,
especially with the increasing concerns surrounding user privacy and data security. Mining sensitive
user data without proper consent can lead to privacy violations and legal ramifications.
Scalability: As the volume of web data continues to grow exponentially, scalability becomes a major
challenge in web mining. Efficient algorithms and techniques are needed to process and analyze
large-scale web data within reasonable timeframes and computational resources.
Dynamic Nature of the Web: The dynamic nature of the web, characterized by constantly changing
content, structures, and user behaviors, poses challenges for web mining. Techniques must adapt to
evolving web environments and handle dynamic data effectively to ensure the accuracy and relevance
of mining results.
Future Trends and Advancements in Web Mining:
Deep Learning for Web Mining: Deep learning techniques, such as neural networks and deep neural
networks, hold great promise for advancing web mining capabilities. These techniques can effectively
handle complex data structures and learn intricate patterns from vast amounts of web data, leading to
more accurate predictions and insights.
Graph-based Mining: With the increasing importance of graph data in various domains, graph-based
mining techniques are expected to gain prominence in web mining. Algorithms for analyzing web
graphs, such as community detection, anomaly detection, and influence analysis, will enable deeper
insights into web structures and user interactions.
Privacy-Preserving Techniques: Given the growing concerns over data privacy, there will be a
greater emphasis on developing privacy-preserving techniques for web mining. Techniques such as
differential privacy, federated learning, and homomorphic encryption will enable mining of sensitive
web data while protecting user privacy and confidentiality.
Real-time Mining: With the advent of real-time web applications and streaming data sources, there
will be an increasing demand for real-time web mining techniques. Algorithms capable of processing
and analyzing data streams in real-time will enable timely insights and decision-making in dynamic
web environments.
Interdisciplinary Approaches: Web mining will continue to evolve as an interdisciplinary field,
drawing insights and techniques from diverse domains such as machine learning, natural language
processing, network science, and human-computer interaction. Integrating techniques from multiple
disciplines will enable more comprehensive and holistic analyses of web data.
In summary, while web mining faces challenges such as data privacy, scalability, and the dynamic
nature of the web, advancements in deep learning, graph-based mining, privacy-preserving
techniques, real-time mining, and interdisciplinary approaches hold promise for addressing these
challenges and driving future innovations in web mining technology.
 CONCLUSION

In conclusion, web mining stands as a powerful and versatile tool for extracting valuable insights and
knowledge from the vast expanse of the World Wide Web. Through techniques such as web content
mining, web structure mining, and web usage mining, researchers and practitioners can uncover
hidden patterns, trends, and relationships within web data, spanning domains such as e-commerce,
social media analysis, and information retrieval.

While web mining offers immense potential for enhancing decision-making, personalization, and
innovation, it is not without its challenges. Issues such as data privacy, scalability, and the dynamic
nature of the web present significant hurdles that must be addressed to ensure the responsible and
ethical use of web mining techniques.

Looking ahead, the future of web mining holds great promise, driven by advancements in deep
learning, graph-based mining, privacy-preserving techniques, real-time mining, and interdisciplinary
approaches. These advancements will enable more accurate predictions, timely insights, and
comprehensive analyses of web data, empowering organizations and individuals to derive greater
value from the wealth of information available on the World Wide Web.

In essence, web mining continues to evolve as a dynamic and interdisciplinary field, poised to shape
the future of information discovery, decision-making, and innovation in the digital age. By navigating
the complexities of web data with ingenuity, responsibility, and foresight, we can harness the full
potential of web mining to create a more informed, connected, and empowered society.
 CHAPTER 9

BIBLIOGRAPHY
[1] Chakrabarti, S., van den Berg, M., & Dom, B. (1999). Focused crawling: a new approach
to topic-specific Web resource discovery. ACM SIGMOD Record, 28(2), 55-61.
[2] Cooley, R., Mobasher, B., & Srivastava, J. (1997). Web mining: information and pattern
discovery on the World Wide Web. In Proceedings of the 9th IEEE International Conference
on Tools with Artificial Intelligence (ICTAI'97) (pp. 558-567). IEEE.
[3] Hotho, A., Nürnberger, A., & Paaß, G. (2005). A brief survey of text mining. LDV
Forum, 20(1), 19-62.
[4] Kleinberg, J. (1999). Authoritative sources in a hyperlinked environment. Journal of the
ACM, 46(5), 604-632.
[5] Mobasher, B., Cooley, R., & Srivastava, J. (2000). Automatic personalization based on
Web usage mining. Communications of the ACM, 43(8), 142-151.
[6] Li, Y., Li, Z., & Li, Y. (2008). A study of e-commerce recommendation based on web
mining technology. In Proceedings of the International Conference on Web Information
Systems and Mining (pp. 177-180). IEEE.
[7] Thelwall, M., Buckley, K., & Paltoglou, G. (2010). Sentiment strength detection for the
social web. Journal of the American Society for Information Science and Technology,
61(12), 2544-2558.
[8] Floridi, L., Taddeo, M., & Turilli, M. (2018). What is data ethics? Philosophical
Transactions of the Royal Society A, 376(2133), 20180081.