Assessing OTT Platform Efficacy Using Data Science and Data Mining Techniques | Chapter 8 | New Horizons of Science, Technology and Culture Vol. 4

 

In the digital era, where internet connectivity shapes lifestyles and choices, traditional modes of entertainment—such as cable television and movie theatres—are gradually witnessing a decline in relevance. In their place, Over-the-Top (OTT) platforms have emerged as the dominant medium of content consumption for a vast segment of the global population. These platforms offer on-demand access to a vast array of content across genres, languages, and formats, redefining how individuals engage with entertainment. Despite their growing ubiquity, a surprising segment of the population—approximately 20%—remains unfamiliar with the term "OTT platforms." Interestingly, nearly half of this segment engages with such services unknowingly through well-known brands like Netflix, Amazon Prime Video, and Disney+, indicating a gap in conceptual understanding despite regular usage.

 

This research paper aims to bridge that knowledge gap and contribute to the broader understanding of OTT platforms from both a consumer and analytical standpoint. The study adopts a data-driven approach, utilising data collected through convenience sampling via structured surveys to assess the depth of public awareness, usage frequency, platform preference, and behavioural trends related to OTT services. It explores consumer sentiment, viewing patterns, subscription tendencies, and satisfaction levels.

 

Furthermore, the paper employs data science and data mining techniques, including machine learning algorithms, to extract meaningful insights from the data. It analyses the correlation between consumer preferences and the performance of different OTT platforms, revealing how content variety, pricing strategies, user interface, and personalisation influence user loyalty and platform success. Sentiment analysis is used to evaluate the public's perception—both positive and negative—about these platforms, underlining the dual nature of technological advancements. By examining these facets, the study not only offers actionable insights for OTT service providers and marketers but also seeks to educate uninformed users about the evolving digital entertainment landscape. This research underlines the growing necessity of digital literacy in media consumption and highlights the transformative impact of data science in decoding user behaviour and platform dynamics in the entertainment industry.

 

 

Author(s) Details

 

Shivani Vats
Jagan Institute of Management Studies, New Delhi, Delhi 110085, India.

 

Disha Grover
Jagan Institute of Management Studies, New Delhi, Delhi 110085, India.

 

 

Please see the book here:- https://doi.org/10.9734/bpi/nhstc/v4/6026

Use of Machine Learning Models for Recommender System of Sentiment Analysis | Chapter 4 | Research Updates in Mathematics and Computer Science Vol. 9

 The study proposes an effective sentiment analysis recommender system framework using machine learning models. Recommender systems are used to build recommendations by processing information from actively gathered varied kinds of data. The data that is used for processing information depends upon the type of recommender system. In recent years, with the rapid growth of Internet technology, online shopping has become a rapid way for users to purchase and consume desired products. Tweet sentiment analysis is a product of the vast amount of user-generated content on social media platforms like Twitter. Sentiment analysis serves as the foundation for recommendation and decision support systems, and it is becoming a crucial tool on online platforms to extract user emotional state data and increase user happiness. 

 

Author(s) Details

A. Naresh

Department of CSE, Annamacharya Institute of Technology and Sciences Autonomous, Kadapa, India.

P. Venkata Krishna

Department of Computer Science, Sri Padmavati Mahila Visvavidyalayam, Tirupati, India.

 

Please see the link:- https://doi.org/10.9734/bpi/rumcs/v9/526

A Survey of Different Text Mining Techniques |Chapter 7 | Text Mining Techniques with Applications, Edition 1

 

In this section, we will provide you with a brief overview of various text mining tasks which are commonly used for analyzing large volumes of unstructured textual data. Text classification, grouping, entity extraction, fine-grained taxonomies, sentiment analysis, document summarization, and entity relation modeling are some of these activities. Text categorization involves organizing text into predefined categories based on its content. Clustering is the process of grouping similar documents together based on their intrinsic characteristics. Entity extraction involves identifying and extracting key elements such as people, places, and organizations from text. Granular taxonomies are hierarchical structures used for organizing textual data. Determining the general sentiment of a text, whether it be favorable, negative, or neutral, is the goal of sentiment analysis. Making a summary of a longer material is called document summarizing. Lastly, the act of determining the connections between various named entities that are stated in a text is known as entity relation modeling.

 

Author(s) Details

Adebola K. Ojo
Department of Computer Science, University of Ibadan, Ibadan, Nigeria.

 

Please see the book here:- https://doi.org/10.9734/bpi/mono/978-81-972870-5-3/CH8

Use of Machine Learning Models for Recommender System of Sentiment Analysis | Chapter 4 | Research Updates in Mathematics and Computer Science Vol. 9

The study proposes an effective sentiment analysis recommender system framework using machine learning models. Recommender systems are used to build recommendations by processing information from actively gathered varied kinds of data. The data that is used for processing information depends upon the type of recommender system. In recent years, with the rapid growth of Internet technology, online shopping has become a rapid way for users to purchase and consume desired products. Tweet sentiment analysis is a product of the vast amount of user-generated content on social media platforms like Twitter. Sentiment analysis serves as the foundation for recommendation and decision support systems, and it is becoming a crucial tool on online platforms to extract user emotional state data and increase user happiness. 

 

Author (s) Details

 

A. Naresh
Department of CSE, Annamacharya Institute of Technology and Sciences Autonomous, Kadapa, India.

P. Venkata Krishna
Department of Computer Science, Sri Padmavati Mahila Visvavidyalayam, Tirupati, India.

 

Please see the book here:- https://doi.org/10.9734/bpi/rumcs/v9/526

Investigation on Sentiment Analysis in Big Data using Machine Learning | Chapter 11 | Research Highlights in Mathematics and Computer Science Vol. 9

 With the arrival of Web 2.0, users have developed a increasing interest in sharing their content, which has happened further amplified apiece emergence of various friendly networking sites. These platforms have supported an excellent opportunity for consumers to share their opinions accompanying people all over the realm. The opinions expressed by consumers on the internet can have a significant affect the service manufacturing. As a result, various industries to a degree educational institutions, analysts, and business organizations are concentrating on opinion excavating, also known as sentiment study (SA), to extract the views and opinions posted for one public. The primary objective of this study search out provide a inclusive overview of sentiment study using machine learning approaches. Furthermore, this paper sheds come to rest on the significant challenges faced by SA, that present a vast purview for future research.

Author(s) Details:

L. Sudha Rani,
CSE Department, GPREC, JNTUA, Anantapur, Kurnool, A. P., India.

S. Zahoor-Ul-Huq,
CSE Department, GPREC, Kurnool , A.P., India.

C. Shoba Bindu,
CSE Department, JNTUA, Anantapur, A.P., India.

Please see the link here: https://stm.bookpi.org/RHMCS-V9/article/view/10419

Sentiment Analysis: An Approach for Analysing Tamil Movie Reviews Using Tamil Tweets | Chapter 4 | Recent Advances in Mathematical Research and Computer Science Vol. 3

 In social media messaging, Indian languages are frequently employed. Tamil is an ancient language that has been utilised frequently in tweets. Sentiment Analysis (SA) is an interdisciplinary field that encompasses both text mining and natural language processing. Sentiment analysis has advanced tremendously in recent years, particularly for the English language. However, there has been relatively little sentiment analysis work done for Indian languages such as Hindi, Tamil, Kannada, and others. The focus of this chapter focuses on Tamil tweets in order to determine the emotion of Tamil movie reviews. It is critical to examine the Tamil language content of tweets in order to gain a sense of the opinions stated in the tweets. The goal is to use Tamil SentiWordNet to classify the sentiment of Tamil films based on Tamil tweets (TSWN). The sentiment polarity of the Tamil movie dataset is determined using the Term Frequency - Inverse Document Frequency (TF-IDF) approach. The fundamental sentiment categorization of Tamil films is determined using domain specific ontology. In contextual semantics, the sentiment of a word can change depending on the word next to it. In this study, sentiment-bearing phrases and their neighbours in Tamil tweets are assessed using contextual semantic sentiment analysis to produce a more accurate outcome for movie sentimental classification.

Author(S) Details

Vallikannu Ramanathan
Department of Computer Science, Alagappa University, Karaikudi, India.

T. Meyyappan
Department of Computer Science, Alagappa University, Karaikudi, India.

S. M. Thamarai
Department of Computer Science, Alagappa Government Arts College, Karaikudi, India.

View Book:- https://stm.bookpi.org/RAMRCS-V3/article/view/4464