Discover and read the best of Twitter Threads about #dataset

Most recents (13)

" Data Analyst Project on Hotel Booking "

That you can add in your resume or portfolio to showcase your skills 💯

🧵
◻ In Recent Year , City Hotel & Resort Hotel have seen High Cancellation Rates. Each Hotel is now Dealing with number of issue as result including Fewer #revenue & Less than ideal Hotel room use.
🔹 Insights :

1️⃣ More Cancellation occur when prices are higher
2️⃣ When there is Longer waiting list , Customer tend to Cancel more frequently
3️⃣ The majority of Clients are coming from a offline #travel agents to make their #reservations
Read 6 tweets
" Exploratory Data Analysis on Terrorism "

🧵
We are performed Exploratory Data Analysis on terrorism #dataset to find out the hot zone of #terrorism. #EDA nothing but #analyzing the given data & finding the #trends, patterns & making some assumptions. #DataVisualization #DataScience #MachineLearning
In this #dataset, there are many features including countries, states, regions, gang names, weapon types, target types, years, months, days, and many more features.
Read 8 tweets
🧠The term Artificial Intelligence is being used as a catch-all for a number of different disciplines but one particular use case may be more important than others: security.

🧐Here's how we use #AI to improve security

🧵👇
First of all, artificial intelligence just means the simulation of human thought by a computer. When you’re using a calculator, you’re already using a computer to “think for you” and do math.

Now you can use a computer to do things like pattern recognition. 🔳🔲🔳🔲🔳🔲
How? The short version is that if you give the computer a step-by-step explanation about how you look at something, you can run it over, and over, and over while correcting its mistakes along the way. 🔁
Read 14 tweets
#TheGlobalAntiHinduScorecard We are glad to publish our first #Top35 Handles list that promote #antiHindu hate on #Twitter. This is from our #March2022 #antiHindu #dataset. Please verify and report the handles. #Hindumisia #Hindudvesha #Hinduphobia 1/2
Please verify and report the handles. We will do the same for subsequent months. Please stay tuned for a #partnership announcement in this regard. #Hindumisia #Hindudvesha #Hinduphobia. 2/2
Please do review and point out if there are any discrepancies. Validation is manual work unfortunately. Model can be improved, but I need more time and dataset to be able to improve the AI Model. Even then it won't be 100%. Data Science is not Exact science!
Read 4 tweets
The last (3rd) day of #PESW2022 is here starting with dr. Luca Cassano from @polimi and his #keynote on "Advances in dependable image processing and deep learning." This talk is an interesting intersection of #AI, #HW and #reliability. Image
NetSec session on Trust and Security in network was launched by me as a chair. We are ready to welcome even remote participant - speaker Jethro Pans from Belgium. The first presentation on security using EC and LoraWAN (IoT long range protocol). Image
Ing. Jan Kala from @FIT_VUT presents now, topic: network traffic #dataset capture, annotated by the developed #webbrowser plugin. Hopefully, #web traffic #ML #classifiers can be trained using the (#IPFIX) datasets. The plugin should work in @googlechrome and @firefox. #PESW2022 Image
Read 4 tweets
How Does a #YouTube Video Go #Viral? We've collected Top Youtubers data using @ZenRowsHQ to see how it grows over time. We used @chartjs for the charts.
zenrows.com/blog/how-does-…
#DataScientists #DataVisualization
We also publish a GitHub repository with a demo and the #dataset
github.com/ZenRows/youtub…
We collected all this data over several days running a recurring Task in Zenrows every 30 minutes. If anyone is interested in trying it out, do not hesitate to contact me. We offer a free tier.
Read 3 tweets
🇪🇺 Key Opinion leaders ⚽

Recently, the failed #EuropeanSuperLeague project set #Twitter on fire.

Between the millions of tweets published on the subject, some voices had a particularly important weight.

Here are the #KOL of European football according to #data:

[THREAD]⤵️
This thread is the continuation of the analysis I shared on the impact of Twitter on the Super League collapse.

The #dataset used is the same: 2.6 million tweets posted by 876,000 unique users in 5 languages (🇬🇧 🇫🇷 🇪🇦 🇮🇹 🇩🇪 )

In my first analysis, I focused on the contents (sentiment analysis, semantic cartographies...), here the goal is to analyze the influential content providers in Europe.
Read 24 tweets
🇪🇺 Leaders d'opinion ⚽

Récemment, le projet avorté #EuropeanSuperLeague a fait s'enflammer #Twitter.

Au cœur des millions de tweets publiés sur le sujet, des voix ont un poids particulièrement important.

Voici les #KOL du foot européen selon la #data :

[THREAD] ⤵️
Ce thread est la suite de l'analyse que j'avais partagé sur l'impact de Twitter dans l'abandon de la Super League.

Le #dataset utilisé est le même : 2,6 millions de tweets postés par 876 000 users uniques dans 5 langues (🇫🇷 🇬🇧 🇪🇦 🇮🇹 🇩🇪 )

Là où dans la première analyse je me consacrais sur les contenus (sentiment analysis, cartographies sémantiques...), ici l'objectif est d'analyser les émetteurs de contenu influents.
Read 25 tweets
Agree. There is a lot more to unpack and there are not simple policy or regulatory fixes. If you think the feds coming down hard on what the population uses to connect and communicate, you’re not a student of history, sociology, psychology, etc.

@sinanaral in @HarvardBiz
I hear all the old, harmful ideas repeated by many who should be at cutting edge of technology. Whereas what @DrvanTilburg describes, if merely digitized to “control” social media, will not work, will harm #SoMe #AI #SciComm #professionalism
From the #healthcare lens there are these potential issues of #AI and #bias including as relates to #COVID19. Yet 30% of business are now using #ArtificialIntelligence in some form. Horse out the barn.

So what is the answer? Ban? Control?

No.

@JordanBazinsky @HealthITNews
Read 14 tweets
Subsequent to #Surgisphere, all @TheLancet journals will now introduce additional peer-review requirements for papers based on large, real-world #datasets. thelancet.com/journals/lance…
@TheLancet journals now require all #research papers, irrespective of method, to include a data-sharing statement that details what #data will be shared, whether additional documents will be shared, when data will become available & by what access criteria data will be shared.
All @TheLancet journals will now introduce additional peer-review requirements for papers based on large, real-world datasets.
Read 10 tweets
As an aspiring #DataScientist, one way to showcase your skills is to build interesting portfolio projects.

Here’s a guide on how to develop interesting data science project ideas & implement them.

Step 1: Choose your passion topic that is relevant.

#DataScience
Step 2: Start Scraping together your own #dataset.

Step 3: Cleaning your dataset (here’s where #datascientists spend about 60% of their time).

Step 4: Data Exploration and Analysis.

Step 5: Share your work on a blog or a popular forum/community.
Read the full article by @FelixVemmer here.
Cc: @Websystemer

A step-by-step guide for creating an authentic data science portfolio project

medium.com/@felix.vemmer/…
Read 3 tweets
Nas últimas 24h adicionamos gráficos no Painel #covid19 do Brasil.IO: dos mais simples, como qtd. de casos confirmados e óbitos, até outros que nos permitem analisar o excesso de óbitos por estado. Segue o fio 👇 #opendata
No último tweet: em azul, casos confirmados acumulados e novos; em vermelho, óbitos acumulados e novos.
Abaixo: causas de óbitos registrados em cartório (@ArpenBrasil). Os gráficos estão disponíveis tanto a nível nacional, quanto estadual - abaixo, o gráfico de óbitos para SP.
Temos também um que compara os óbitos totais entre 2019 e 2020 agrupados em 3 grandes grupos: #covid19 (suspeitos e confirmados), outras causas respiratórias e outras causas naturais não externas. Repare que a barra azul tem pouca variação, enquanto verde e vermelho crescem:
Read 10 tweets
Automation Tools To Ease Your Data Science Project

Working on Data Science Project can be overwhelming for beginners esp student that intend to carry our a research in this field.

Below are some automation tools that data science professional can use.
#DataScience #Thread
1 WEKA
Weka is a collection of machine learning algorithms for data mining tasks. It contains tools for data preparation, classification, regression, clustering, association rules mining, and visualization
#WEKA help you discover practical data mining &learn to mine your own data
#WEKA make it easy for you to play around with data and it gives you test options regarding how you split your #dataset.
I once used WEKA to get result 'clue' for Classification of EEG signal using AIRS, Immuno, CLONALG.

Download WEKA: cs.waikato.ac.nz/ml/weka/
Read 11 tweets

Related hashtags

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3.00/month or $30.00/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!