<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Abirami .M on Medium]]></title>
        <description><![CDATA[Stories by Abirami .M on Medium]]></description>
        <link>https://medium.com/@abiramim.abt?source=rss-48d7b57ec192------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/0*GKDemOxTs8jCd9iK</url>
            <title>Stories by Abirami .M on Medium</title>
            <link>https://medium.com/@abiramim.abt?source=rss-48d7b57ec192------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Thu, 19 Nov 2026 09:41:30 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@abiramim.abt/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[My Experience in Applied NLP & Language Intelligence — From Text Analytics to Generative AI]]></title>
            <link>https://medium.com/@abiramim.abt/my-experience-in-applied-nlp-language-intelligence-from-text-analytics-to-generative-ai-23dede45ebdd?source=rss-48d7b57ec192------2</link>
            <guid isPermaLink="false">https://medium.com/p/23dede45ebdd</guid>
            <category><![CDATA[generative-ai]]></category>
            <category><![CDATA[spam-detection]]></category>
            <category><![CDATA[text-analytics]]></category>
            <category><![CDATA[natural-language-process]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <dc:creator><![CDATA[Abirami .M]]></dc:creator>
            <pubDate>Mon, 25 May 2026 10:59:50 GMT</pubDate>
            <atom:updated>2026-05-25T10:59:50.879Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*4d6E0yUVzNqCYjrkXCIOWQ.png" /></figure><h3>Exploring Natural Language Processing, Machine Learning, and Generative AI</h3><p>As part of my learning journey in Artificial Intelligence and Data Science, I had the opportunity to work on <strong>Applied NLP (Natural Language Processing) &amp; Language Intelligence</strong>. This experience helped me understand how machines process, analyze, and interpret human language using AI and machine learning techniques.</p><p>Through this training, I gained both theoretical knowledge and practical implementation experience in building NLP-based applications.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/950/1*YMM2Lck4xx5kCLjLpj7iEQ.jpeg" /></figure><h3>Understanding the Fundamentals of NLP</h3><p>One of the first things I learned was the complete <strong>NLP workflow</strong>, starting from text preprocessing techniques used to clean raw textual data before applying machine learning models.</p><h3>Text Preprocessing Techniques I Learned</h3><p>The preprocessing stage included:</p><ul><li>Lowercasing text</li><li>Removing punctuation</li><li>Stopword removal</li><li>Tokenization</li><li>Stemming</li><li>Lemmatization</li></ul><p>These techniques helped me understand how unstructured text data is converted into a clean and machine-readable format.</p><h3>Learning Text Representation Techniques</h3><p>After preprocessing, I explored different <strong>feature extraction and text representation methods</strong> used in Natural Language Processing.</p><h3>Techniques I Worked With</h3><p>✔ Bag of Words (BoW)<br> ✔ TF-IDF (Term Frequency–Inverse Document Frequency)<br> ✔ N-grams<br> ✔ Word Embeddings</p><p>These methods taught me how textual information can be transformed into numerical vectors for machine learning applications.</p><p>I also learned advanced embedding models such as:</p><ul><li>Word2Vec</li><li>GloVe</li></ul><p>These techniques improved my understanding of semantic relationships between words and contextual meaning in language processing.</p><h3>Exploring Deep Learning in NLP</h3><p>One of the most interesting parts of this learning experience was understanding how deep learning models process sequential text data.</p><h3>Sequence Models I Explored</h3><p>✔ LSTM (Long Short-Term Memory)<br> ✔ GRU (Gated Recurrent Unit)</p><p>These models helped me understand how AI systems capture contextual information and dependencies in language.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*G_TSkcRtMzhkZp_Da4xZZA.png" /></figure><h3>Introduction to Transformers &amp; Generative AI</h3><p>I was also introduced to advanced NLP architectures such as:</p><p>✔ Transformers<br> ✔ BERT (Bidirectional Encoder Representations from Transformers)</p><p>Learning these modern architectures gave me insight into how current AI systems and generative AI tools understand and generate human language.</p><p>This helped me understand the foundation behind:</p><ul><li>Chatbots</li><li>AI assistants</li><li>Text generation systems</li><li>Intelligent language models</li></ul><h3>Final NLP Project — Spam Detection System</h3><p>As part of the final NLP project, I implemented a <strong>Spam Detection System using TF-IDF and Naive Bayes Classification</strong>.</p><h3>Project Workflow</h3><p>The project included:</p><ul><li>Data preprocessing</li><li>Text cleaning</li><li>Feature extraction using TF-IDF</li><li>Model training using Naive Bayes</li><li>Model evaluation</li><li>Prediction testing</li></ul><p>I also evaluated the model using:</p><ul><li>Accuracy score</li><li>Confusion Matrix</li></ul><p>This practical implementation improved my:<br> ✔ Python programming skills<br> ✔ Machine learning understanding<br> ✔ Confidence in building NLP-based applications</p><p># ============================================================<br># SMS SPAM DETECTION PROJECT<br># ============================================================</p><p># ============================================================<br># IMPORT LIBRARIES<br># ============================================================</p><p>import pandas as pd<br>import numpy as np<br>import re<br>import seaborn as sns<br>import matplotlib.pyplot as plt</p><p>from sklearn.model_selection import train_test_split<br>from sklearn.feature_extraction.text import TfidfVectorizer<br>from sklearn.naive_bayes import MultinomialNB</p><p>from sklearn.metrics import accuracy_score<br>from sklearn.metrics import confusion_matrix<br>from sklearn.metrics import classification_report</p><p># ============================================================<br># LOAD DATASET<br># ============================================================</p><p>dataset_path = r”D:\mini project\dataset\spam.csv”</p><p>df = pd.read_csv(dataset_path, encoding=’latin-1&#39;)</p><p># ============================================================<br># SHOW FIRST 5 ROWS<br># ============================================================</p><p>print(“\nFIRST 5 ROWS”)<br>print(df.head())</p><p># ============================================================<br># KEEP ONLY REQUIRED COLUMNS<br># ============================================================</p><p>df = df[[‘v1’, ‘v2’]]</p><p># Rename columns<br>df.columns = [‘label’, ‘message’]</p><p># ============================================================<br># LABEL ENCODING<br># ham = 0<br># spam = 1<br># ============================================================</p><p>df[‘label’] = df[‘label’].map({<br> ‘ham’: 0,<br> ‘spam’: 1<br>})</p><p>print(“\nDATASET INFO”)<br>print(df.head())</p><p># ============================================================<br># TEXT CLEANING FUNCTION<br># ============================================================</p><p>def clean_text(text):</p><p># Convert to lowercase<br> text = text.lower()</p><p># Remove punctuation<br> text = re.sub(r’[^\w\s]’, ‘’, text)</p><p># Remove numbers<br> text = re.sub(r’\d+’, ‘’, text)</p><p>return text</p><p># Apply cleaning<br>df[‘message’] = df[‘message’].apply(clean_text)</p><p># ============================================================<br># INPUT FEATURES AND LABELS<br># ============================================================</p><p>X_text = df[‘message’]</p><p>y = df[‘label’]</p><p># ============================================================<br># TF-IDF FEATURE EXTRACTION<br># ============================================================</p><p>tfidf = TfidfVectorizer()</p><p>X = tfidf.fit_transform(X_text)</p><p>print(“\nTF-IDF SHAPE”)<br>print(X.shape)</p><p># ============================================================<br># TRAIN TEST SPLIT<br># ============================================================</p><p>X_train, X_test, y_train, y_test = train_test_split(<br> X,<br> y,<br> test_size=0.2,<br> random_state=42<br>)</p><p>print(“\nTRAINING DATA SHAPE :”, X_train.shape)<br>print(“TESTING DATA SHAPE :”, X_test.shape)</p><p># ============================================================<br># MODEL TRAINING<br># ============================================================</p><p>model = MultinomialNB()</p><p>model.fit(X_train, y_train)</p><p>print(“\nMODEL TRAINING COMPLETED”)</p><p># ============================================================<br># PREDICTION<br># ============================================================</p><p>y_pred = model.predict(X_test)</p><p>print(“\nPREDICTION COMPLETED”)</p><p># ============================================================<br># ACCURACY<br># ============================================================</p><p>acc = accuracy_score(y_test, y_pred)</p><p>print(“\nMODEL ACCURACY :”, acc)</p><p># ============================================================<br># CONFUSION MATRIX<br># ============================================================</p><p>cm = confusion_matrix(y_test, y_pred)</p><p>print(“\nCONFUSION MATRIX”)<br>print(cm)</p><p># ============================================================<br># CONFUSION MATRIX VISUALIZATION<br># ============================================================</p><p>plt.figure(figsize=(6,5))</p><p>sns.heatmap(<br> cm,<br> annot=True,<br> fmt=’d’,<br> cmap=’Blues’<br>)</p><p>plt.title(<br> “CONFUSION MATRIX”,<br> fontsize=14,<br> fontweight=’bold’<br>)</p><p>plt.xlabel(<br> “PREDICTED”,<br> fontsize=12,<br> fontweight=’bold’<br>)</p><p>plt.ylabel(<br> “ACTUAL”,<br> fontsize=12,<br> fontweight=’bold’<br>)</p><p>plt.show()</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/589/1*nANJqDd23WMm5dKSsFgDQA.png" /></figure><p># ============================================================<br># CLASSIFICATION REPORT<br># ============================================================</p><p>report = classification_report(<br> y_test,<br> y_pred<br>)</p><p>print(“\nCLASSIFICATION REPORT”)<br>print(report)</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/512/1*TUmyeviRGFSxaDVDeQxNKw.png" /></figure><p># ============================================================<br># CUSTOM MESSAGE PREDICTION<br># ============================================================</p><p>sample = [“Congratulations! You won free cash”]</p><p># Clean sample text<br>sample = [clean_text(text) for text in sample]</p><p># Convert to TF-IDF<br>sample_vector = tfidf.transform(sample)</p><p># Predict<br>prediction = model.predict(sample_vector)</p><p>print(“\nCUSTOM MESSAGE PREDICTION”)</p><p>if prediction[0] == 1:<br> print(“SPAM MESSAGE”)<br>else:<br> print(“HAM MESSAGE”)</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/387/1*oS6_l_W-0UnT0Vm-UYaXqw.png" /></figure><h3>Real-World Applications I Learned</h3><p>Through this course, I understood how NLP is used in real-world applications such as:</p><ul><li>Sentiment Analysis</li><li>Spam Detection</li><li>Chatbots</li><li>Customer Feedback Analysis</li><li>Social Media Monitoring</li><li>Intelligent AI Systems</li></ul><h3>💡 My Biggest Learning</h3><blockquote><em>NLP is not just about processing text — it is about enabling machines to understand human communication intelligently.</em></blockquote><p>This experience significantly enhanced my knowledge in:</p><ul><li>Machine Learning</li><li>Deep Learning</li><li>Language Intelligence Systems</li><li>Generative AI Concepts</li></ul><h3>Conclusion</h3><p>Overall, working on <strong>Applied NLP &amp; Language Intelligence — From Text Analytics to Generative AI</strong> was an extremely valuable learning experience for me.</p><p>It gave me hands-on exposure to:<br> ✔ NLP preprocessing<br> ✔ Text analytics<br> ✔ Machine learning models<br> ✔ Deep learning architectures<br> ✔ Generative AI foundations</p><p>This journey strengthened my interest in Artificial Intelligence and motivated me to continue exploring advanced AI technologies and real-world intelligent systems.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=23dede45ebdd" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[My 30-Day Journey into Digital Marketing (Day 1–7 Learnings for Beginners) ]]></title>
            <link>https://medium.com/@abiramim.abt/my-30-day-journey-into-digital-marketing-day-1-7-learnings-for-beginners-cddf9f3c17de?source=rss-48d7b57ec192------2</link>
            <guid isPermaLink="false">https://medium.com/p/cddf9f3c17de</guid>
            <category><![CDATA[content-writing]]></category>
            <category><![CDATA[beginner-guide]]></category>
            <category><![CDATA[digital-marketing]]></category>
            <category><![CDATA[blogging]]></category>
            <category><![CDATA[seo]]></category>
            <dc:creator><![CDATA[Abirami .M]]></dc:creator>
            <pubDate>Mon, 11 May 2026 10:24:12 GMT</pubDate>
            <atom:updated>2026-05-11T10:24:12.659Z</atom:updated>
            <content:encoded><![CDATA[<h3><strong>My 30-Day Journey into Digital Marketing (Day 1–7 Learnings for Beginners)</strong></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*TWirN5JXRT979bJqzQrJXQ.jpeg" /></figure><h3>Beginner Experience in Digital Marketing | Content Writing | SEO Basics</h3><p>Over the past week, I started my journey into <strong>Digital Marketing</strong> from scratch. With zero prior experience, my goal is to understand how online marketing works and how brands grow using digital platforms like Google, Instagram, and websites.</p><p>This article is a part of my <strong>30-day learning journey</strong>, where I document everything I learn step by step.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*YX83j_2ZCIystPnuyYbKIg.jpeg" /></figure><h3>What is Digital Marketing?</h3><p>Digital Marketing is the process of promoting products or services using online platforms such as:</p><ul><li>Google Search</li><li>Social Media (Instagram, Facebook, LinkedIn)</li><li>Websites and Blogs</li><li>Email Marketing</li></ul><p>It helps businesses reach the right audience at the right time using the internet.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*qVw949MG9RSix7xS84RdvQ.jpeg" /></figure><h3>Day 1–7 Learnings Summary</h3><h3>1. Basics of Digital Marketing</h3><p>Digital marketing is all about connecting businesses with customers online. It includes strategies like SEO, content creation, social media marketing, and paid ads.</p><p>👉 Key Idea: Everything happens online, and visibility is everything.</p><h3>2. Content Writing Basics</h3><p>Content is the <strong>foundation of digital marketing</strong>.</p><p>Good content should be:</p><ul><li>Simple and easy to understand</li><li>Helpful to the reader</li><li>Clear and engaging</li><li>Free from unnecessary complexity</li></ul><p>👉 Lesson: If content is strong, marketing becomes easier.</p><h3>3. Introduction to SEO (Search Engine Optimization)</h3><p>SEO helps websites appear on Google search results.</p><p>It works by:</p><ul><li>Using relevant keywords</li><li>Writing quality content</li><li>Improving website structure</li><li>Building authority through links</li></ul><p>👉 Goal: Rank higher on Google and get organic traffic.</p><h3>4. Understanding Keywords</h3><p>Keywords are the words people type on Google.</p><p>Example:</p><ul><li>“Best digital marketing course”</li><li>“How to start freelancing”</li></ul><p>👉 Why it matters:<br> Using the right keywords helps your content reach the right audience.</p><h3>5. On-Page vs Off-Page SEO</h3><p>🔹 On-Page SEO:<br> Optimizing inside the website (content, headings, keywords, images)</p><p>🔹 Off-Page SEO:<br> External activities like backlinks, social sharing, and brand mentions</p><p>👉 Simple Idea:<br> On-page = inside control<br> Off-page = outside growth</p><h3>My Biggest Learning So Far</h3><blockquote><strong><em>Consistency is more powerful than perfection.</em></strong></blockquote><blockquote>Even small daily learning builds strong skills over time.<br> Progress matters more than being perfect from day one.</blockquote><h3>Conclusion</h3><p>This first week helped me understand the <strong>core foundation of digital marketing</strong>. I will continue learning SEO, social media marketing, and freelancing platforms like Fiverr and Upwork in the upcoming days.</p><p>This is just the beginning of my journey.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=cddf9f3c17de" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[SEO for Beginners: Step-by-Step Guide to Rank #1 on Google (2026)]]></title>
            <link>https://medium.com/@abiramim.abt/seo-for-beginners-step-by-step-guide-to-rank-1-on-google-2026-07692e717c51?source=rss-48d7b57ec192------2</link>
            <guid isPermaLink="false">https://medium.com/p/07692e717c51</guid>
            <category><![CDATA[seo]]></category>
            <category><![CDATA[digital-marketing]]></category>
            <category><![CDATA[blogging]]></category>
            <category><![CDATA[content-writing]]></category>
            <dc:creator><![CDATA[Abirami .M]]></dc:creator>
            <pubDate>Wed, 06 May 2026 09:56:55 GMT</pubDate>
            <atom:updated>2026-05-06T10:03:19.879Z</atom:updated>
            <content:encoded><![CDATA[<h3>Introduction</h3><p>Want to learn SEO but don’t know where to start? This beginner-friendly guide will help you understand SEO step by step and show you how to rank your content on Google easily. Whether you are a student, blogger, or freelancer, this guide will help you learn SEO basics in a simple way.</p><h3>What is SEO?</h3><p>SEO (Search Engine Optimization) is the process of improving your website so it appears higher on search engines like Google. It helps people find your content when they search for related topics. Learning SEO is important because it brings free traffic to your website.</p><h3>Why SEO is Important</h3><p>SEO helps you get organic (free) traffic without spending money on ads. When your content ranks on Google, more people visit your website. This can help you grow a blog, business, or freelancing career.</p><h3>How SEO Works</h3><p>SEO works based on how search engines rank websites. There are three main steps:</p><ul><li>Crawling: Search engines scan websites</li><li>Indexing: They store the information</li><li>Ranking: They decide which page appears first</li></ul><p>Your website ranks based on keywords, content quality, backlinks, and user experience.</p><h3>Types of SEO</h3><h3>1. On-Page SEO</h3><p>On-page SEO focuses on optimizing your content:</p><ul><li>Use keywords naturally</li><li>Write proper headings</li><li>Add meta descriptions</li><li>Optimize images</li></ul><h3>2. Off-Page SEO</h3><p>Off-page SEO builds your website authority:</p><ul><li>Get backlinks from other websites</li><li>Share content on social media</li></ul><h3>3. Technical SEO</h3><p>Technical SEO improves website performance:</p><ul><li>Fast loading speed</li><li>Mobile-friendly design</li><li>Clean URL structure</li></ul><h3>Keyword Research Basics</h3><p>Keywords are the words people search on Google. Beginners should focus on long-tail keywords like:</p><ul><li>SEO for beginners</li><li>Learn SEO step by step</li><li>SEO basics for students</li></ul><p>Use tools like Google suggestions and related searches to find keywords.</p><h3>Step-by-Step SEO Process for Beginners</h3><ol><li>Choose a keyword</li><li>Understand search intent</li><li>Write helpful content</li><li>Use headings (H1, H2, H3)</li><li>Optimize title and meta description</li><li>Add internal links</li><li>Share your content</li></ol><h3>Simple SEO Tips for Beginners</h3><ul><li>Use your keyword in the title</li><li>Write clear and simple content</li><li>Use short paragraphs</li><li>Learn from top-ranking websites</li><li>Be consistent in posting</li></ul><h3>Frequently Asked Questions</h3><h3>❓ What is SEO in simple words?</h3><p>SEO is the process of improving your website to rank higher on search engines like Google.</p><h3>❓ Can beginners learn SEO?</h3><p>Yes, anyone can learn SEO with practice and consistency.</p><h3>❓ How long does SEO take?</h3><p>SEO usually takes a few weeks to months to show results.</p><h3>Conclusion</h3><p>SEO for beginners may seem difficult at first, but it becomes easier with practice. By learning keywords, content optimization, and how search engines work, you can start ranking your content. SEO is a powerful skill that can help you build a career, grow a business, or earn money online.</p><p><em>“Follow me on Medium for more SEO and digital marketing tips.”</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=07692e717c51" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>