{"id":15103619,"url":"https://github.com/atharvapathak/customer_sentiment_analysis","last_synced_at":"2026-02-21T10:01:38.814Z","repository":{"id":232560549,"uuid":"784641876","full_name":"atharvapathak/Customer_Sentiment_Analysis","owner":"atharvapathak","description":"Customer sentiment analysis is the process of using natural language processing (NLP) and machine learning techniques to analyze and understand the feelings, opinions, and attitudes expressed by customers in textual data, such as reviews, feedback, and social media posts.","archived":false,"fork":false,"pushed_at":"2024-04-10T09:00:13.000Z","size":67,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-18T14:13:48.136Z","etag":null,"topics":["cnn","naive-bayes","nlp","nltk","spacy","stemming","text-mining","tokenization"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/atharvapathak.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2024-04-10T08:57:42.000Z","updated_at":"2024-04-10T09:23:18.000Z","dependencies_parsed_at":"2024-04-10T10:06:44.939Z","dependency_job_id":"8dfa8728-debf-4f8f-b766-19fa7bc4d872","html_url":"https://github.com/atharvapathak/Customer_Sentiment_Analysis","commit_stats":null,"previous_names":["atharvapathak/customer_sentiment_analysis"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/atharvapathak/Customer_Sentiment_Analysis","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atharvapathak%2FCustomer_Sentiment_Analysis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atharvapathak%2FCustomer_Sentiment_Analysis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atharvapathak%2FCustomer_Sentiment_Analysis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atharvapathak%2FCustomer_Sentiment_Analysis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/atharvapathak","download_url":"https://codeload.github.com/atharvapathak/Customer_Sentiment_Analysis/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atharvapathak%2FCustomer_Sentiment_Analysis/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29679049,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-21T09:33:50.764Z","status":"ssl_error","status_checked_at":"2026-02-21T09:33:19.949Z","response_time":107,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cnn","naive-bayes","nlp","nltk","spacy","stemming","text-mining","tokenization"],"created_at":"2024-09-25T19:40:52.522Z","updated_at":"2026-02-21T10:01:38.573Z","avatar_url":"https://github.com/atharvapathak.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Sentiment Analysis on Customer Reviews\n### Text engineering course\n\nThis repository holds the implementation of the 2nd (second) assignment for the Text Engineering and Analytics course, which is part of the M.Sc. in Data Science program of the Athens University of Economics and Business.\n\n### Assignment Description:\n\n1. Develop a text classifier for a kind of texts of your choice (e.g., e-mail messages, tweets,\ncustomer reviews) and at least two classes (e.g., spam/ham, positive/negative/neutral)*.\n2. You may use Boolean, TF, or TF-IDF features corresponding to words or n-grams, to which you\ncan also add other features (e.g., length of the text). You may apply any feature selection (or\ndimensionality reduction) method you consider appropriate. You may also want to try using\ncentroids of pre-trained word embeddings (slide 36).\n3. You can write your own code to produce feature vectors, perform feature selection (or dimensionality reduction)\nand train the classifier (e.g., using SGD and the tricks of slides 59–60, in the case of logistic regression), or\nyou can use existing implementations and software libraries.\n4. You should experiment with at least logistic regression, and optionally other learning algorithms \n(e.g., Naive Bayes, k-NN, SVM). Draw learning curves (slides 66, 69) with appropriate measures (e.g., accuracy, F1)\nand precision-recall curves (slide 24). Include experimental results of appropriate baselines\n(e.g., majority classifiers). Make sure that you use separate training and test data. Tune the\nfeature set and hyper-parameters (e.g., regularization weight λ) on a held-out part of the\ntraining data or using a cross-validation (slide 26) on the training data. Document clearly in a\nshort report (max. 5 pages) how your system works (e.g., what algorithms it uses, examples of\ninput/output) and its experimental results (e.g., learning curves, precision-recall curves).\n\n\n* For e-mail spam filtering, you may want to use the Ling-Spam or Enron-Spam datasets (available\nfrom http://nlp.cs.aueb.gr/software.html). For tweets, you may want to use datasets from\nhttp://alt.qcri.org/semeval2016/task4/. For customer reviews, you may want to use datasets from\nhttp://alt.qcri.org/semeval2016/task5/. Consult the instructor for further details.\n* Pre-trained word embeddings are available, for example, from http://nlp.stanford.edu/projects/glove/.\nSee also word2vec (https://code.google.com/archive/p/word2vec/). \n\n# Implementation Details\n\n## Getting started\nThe following instructions will get you a copy of the project up and running on your local machine for development and testing purposes.\n\n### Installing\nIn order to run the code in your local environment, please make sure your have python 3. and above and to have installed the needed python libraries.\nTo install the libraries please run on your console:\n\n```\npip install -r requirements.txt file\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatharvapathak%2Fcustomer_sentiment_analysis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fatharvapathak%2Fcustomer_sentiment_analysis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatharvapathak%2Fcustomer_sentiment_analysis/lists"}