Dataconomy
  • News
  • AI
  • Big Data
  • Machine Learning
  • Trends
    • Blockchain
    • Cybersecurity
    • FinTech
    • Gaming
    • Internet of Things
    • Startups
    • Whitepapers
  • Industry
    • Energy & Environment
    • Finance
    • Healthcare
    • Industrial Goods & Services
    • Marketing & Sales
    • Retail & Consumer
    • Technology & IT
    • Transportation & Logistics
  • Events
  • About
    • About Us
    • Contact
    • Imprint
    • Legal & Privacy
    • Newsletter
    • Partner With Us
    • Writers wanted
Subscribe
No Result
View All Result
Dataconomy
  • News
  • AI
  • Big Data
  • Machine Learning
  • Trends
    • Blockchain
    • Cybersecurity
    • FinTech
    • Gaming
    • Internet of Things
    • Startups
    • Whitepapers
  • Industry
    • Energy & Environment
    • Finance
    • Healthcare
    • Industrial Goods & Services
    • Marketing & Sales
    • Retail & Consumer
    • Technology & IT
    • Transportation & Logistics
  • Events
  • About
    • About Us
    • Contact
    • Imprint
    • Legal & Privacy
    • Newsletter
    • Partner With Us
    • Writers wanted
Subscribe
No Result
View All Result
Dataconomy
No Result
View All Result

Data Around The World – Part III: No 3G, No Fun

by Marianne Faro
September 9, 2016
in Contributors, News, Transportation & Logistics
Home Contributors
Share on FacebookShare on TwitterShare on LinkedInShare on WhatsAppShare on e-mail

Last week, the STORM team drove through Turkmenistan – the only country in the tour with no KPN 3G connectivity. So there were a few days with no real-time data coming in. In order to still be able to follow the tour, we created some simple predictions based on latitude and longitude, Google traffic info, the planned route, and historical data on average speed.

Since there was also no real-time data coming in on start and stop of the stage drive, we had the STORM team send us a text message at departure and arrival. We then manually entered them into the analytics platform. Indeed, quite the sophisticated way of data transfer.

Due to the mostly-missing internet connection we also did not receive data from the motorcycle via the CAN bus (the messaging network used by all components of the motorcycle to exchange measurements, events and orders). We use this data to determine the battery’s state of charge, the voltages of the individual battery cells and the speed, among other things.

That is why this week’s data analysis focuses on the STORM data that we actually have – such as tweets and visits of the website to follow STORM.

In the Itility data analysis methodology we start out with some simple visualizations of the data. The graph below shows that tweets (with the #Storm80days hashtag) are coming in at a positive rate of between 1 and 20 per hour, fewer during night time and more in the afternoon / evening.


Join the Partisia Blockchain Hackathon, design the future, gain new skills, and win!


080916-tweets-per-hour

The next step is to dive a little deeper in the data to understand what’s going on. Because STORM is an interesting project by young students, we expected the tweets to contain mostly positive messages. Sentiment analysis (based on both the English and Dutch sentiment word lists) on those tweets shows the pattern below– a constant positive and neutral flow, with a minuscule line of “negative”, proving our hypothesis and providing a base for further investigations.

080916-positive-negative-tweets

Digging deeper into the tweets marked as “negative”, we found that most of those tweets where actually not very negative but they contained words like “missed” and “raining”. Tweets that are actually negative are tweets about a bad night of sleep (due to a gas leak and a bed breaking down).

Now that we knew a little more about the messages with the hashtag #Storm80Days, we wanted to know more about related hashtags. The hashtags that are used change on a daily basis. They are picked depending on where the STORM team is giving presentations or doing events. To gain more visibility of the used hashtags, we created a dynamic word cloud. The cloud is updated in real-time to show the hashtags used in combination with #Storm80Days. In the image below you can see that the location of the motorcycle is often used as hashtag. Coincidentally, STORM team member Maartje Verhoek was nominated for “TechGirl of the month” . During the last days of August, #techgirl was frequently used. In case you were wondering – she won! Congratulations Maartije for being TechGirl of the month of August!

280816-tweet-wordcloud

The next step is to find correlations in the data. We tried to find correlations between words in tweets posted in the early days of the tour, showing quite obvious correlations.

correlatedwords

Because the correlation between words in tweets is not really interesting, due to very predictable results, we tried to find a correlation between website visits and tweets. We expected that the number of tweets is related to the number of website visits, because visitors would tweet about the website. In the picture below you can see that we were somewhat right:

correlation

There is a strong correlation in the center of the graph, between August 20 and September 1.

Keep following Storm via follow.storm-eindhoven.nl. We will post new updates and analysis results on a daily basis!

Like this article? Subscribe to our weekly newsletter to never miss out!

Follow @DataconomyMedia

Tags: data analyticsItilitySTORM Wave

Related Posts

How did ChatGPT passed an MBA exam

How did ChatGPT passed an MBA exam?

February 2, 2023
Google code red: ChatGPT and You.com like AI-powered tools threatening the search engine. Moreover, latest Apple Search rumors increased the danger.

Google code red: ChatGPT, You.com and rumors of Apple Search challenge the dominance of search giant

February 2, 2023
Examples of artificial intelligence in supply chain management

Unleashing the power of AI with the rise of intelligent supply chain management

January 23, 2023
T-Mobile data breach 2023 explained: Learn how did the leak happen and explore T-Mobile data breach history. It is not the first time of the company

T-Mobile data breach 2023: The telecom giant got hacked eight times in the last six years

January 20, 2023
Microsoft layoffs 2023: Amazon job cuts that affect 11,000 employees explained. Big tech layoffs continue... Learn why and what will happen next.

Microsoft layoffs will affect more than 11,000 employees

January 18, 2023
Medibank Data Breach Class Action: Compensation can reach up to $20,000 per person

Medibank Data Breach Class Action: Compensation can reach up to $20,000 per person

January 16, 2023

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

LATEST ARTICLES

Cyberpsychology: The psychological underpinnings of cybersecurity risks

ChatGPT Plus: How does the paid version work?

AI Text Classifier: OpenAI’s ChatGPT detector indicates AI-generated text

A journey worth taking: Shifting from BPM to DPA

BuzzFeed ChatGPT integration: Buzzfeed stock surges after the OpenAI deal

Adversarial machine learning 101: A new cybersecurity frontier

Dataconomy

COPYRIGHT © DATACONOMY MEDIA GMBH, ALL RIGHTS RESERVED.

  • About
  • Imprint
  • Contact
  • Legal & Privacy
  • Partnership
  • Writers wanted

Follow Us

  • News
  • AI
  • Big Data
  • Machine Learning
  • Trends
    • Blockchain
    • Cybersecurity
    • FinTech
    • Gaming
    • Internet of Things
    • Startups
    • Whitepapers
  • Industry
    • Energy & Environment
    • Finance
    • Healthcare
    • Industrial Goods & Services
    • Marketing & Sales
    • Retail & Consumer
    • Technology & IT
    • Transportation & Logistics
  • Events
  • About
    • About Us
    • Contact
    • Imprint
    • Legal & Privacy
    • Newsletter
    • Partner With Us
    • Writers wanted
No Result
View All Result
Subscribe

This website uses cookies. By continuing to use this website you are giving consent to cookies being used. Visit our Privacy Policy.