{"id":2130,"date":"2026-03-29T12:35:26","date_gmt":"2026-03-29T16:35:26","guid":{"rendered":"http:\/\/wordpress-473092-1485251.cloudwaysapps.com\/?p=2130"},"modified":"2026-03-29T12:35:26","modified_gmt":"2026-03-29T16:35:26","slug":"demonstrating-analytics-as-a-service-via-twitter-hashtag-analysis-in-watson-analytics","status":"publish","type":"post","link":"https:\/\/www.data-mania.com\/blog\/demonstrating-analytics-as-a-service-via-twitter-hashtag-analysis-in-watson-analytics\/","title":{"rendered":"Demonstrating Analytics-as-a-Service with Twitter Hashtag Analysis in Watson Analytics"},"content":{"rendered":"<p style=\"text-align: justify;\">For our last installment in this 3-part series on <a href=\"http:\/\/data-mania.com\/blog\/analytics-as-a-service-will-watson-analytics-replace-the-data-science-role\/\">analytics-as-a-service<\/a>, I\u2019m going to provide you a quick and dirty demonstration of how to use Watson Analytics to analyze hashtag data from the Twitter social network.<\/p>\n<h2 style=\"text-align: justify;\">Step 1: Log-in to Watson Analytics and Add Your Data<\/h2>\n<p><a href=\"http:\/\/data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-2.png\"><img decoding=\"async\" class=\"aligncenter size-full wp-image-2132 lazyload\" data-src=\"http:\/\/data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-2.png\" alt=\"Create-a-dataset-2\" width=\"798\" height=\"494\" data-srcset=\"https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-2.png 798w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-2-300x186.png 300w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-2-768x475.png 768w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-2-90x56.png 90w\" data-sizes=\"auto, (max-width: 798px) 100vw, 798px\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" style=\"--smush-placeholder-width: 798px; --smush-placeholder-aspect-ratio: 798\/494;\" \/><\/a><\/p>\n<p style=\"text-align: justify;\">Once you get inside of Watson Analytics, you\u2019re going to see a menu that looks like the one shown above. Click on \u2018Upload data\u2019 in the \u2018Or add your data\u2019 section.<\/p>\n<p style=\"text-align: justify;\"><a href=\"http:\/\/data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-3.png\"><img decoding=\"async\" class=\"aligncenter size-full wp-image-2133 lazyload\" data-src=\"http:\/\/data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-3.png\" alt=\"Create-a-dataset-3\" width=\"799\" height=\"487\" data-srcset=\"https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-3.png 799w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-3-300x183.png 300w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-3-768x468.png 768w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-3-90x55.png 90w\" data-sizes=\"auto, (max-width: 799px) 100vw, 799px\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" style=\"--smush-placeholder-width: 799px; --smush-placeholder-aspect-ratio: 799\/487;\" \/><\/a><\/p>\n<p style=\"text-align: justify;\">That will take you to this next menu that is shown above. We are doing a Twitter data analysis, so choose the \u2018Twitter\u2019 option here.<\/p>\n<p style=\"text-align: justify;\"><a href=\"http:\/\/data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-4.png\"><img decoding=\"async\" class=\"aligncenter size-full wp-image-2134 lazyload\" data-src=\"http:\/\/data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-4.png\" alt=\"Create-a-dataset-4\" width=\"800\" height=\"493\" data-srcset=\"https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-4.png 800w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-4-300x185.png 300w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-4-768x473.png 768w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-4-90x55.png 90w\" data-sizes=\"auto, (max-width: 800px) 100vw, 800px\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" style=\"--smush-placeholder-width: 800px; --smush-placeholder-aspect-ratio: 800\/493;\" \/><\/a><\/p>\n<p style=\"text-align: justify;\">Watson Analytics\u2019 Twitter data analysis feature allows you to query data out from Twitter, based on hashtags, language, start date and end date. The hashtags I entered for this exploration were:<\/p>\n<ul style=\"text-align: justify;\">\n<li>#BigData<\/li>\n<li>#DataScience<\/li>\n<li>#Algorithms<\/li>\n<li>#MachineLearning<\/li>\n<li>#Analytics<\/li>\n<li>#DataAnalytics<\/li>\n<\/ul>\n<p><a href=\"http:\/\/data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-5.png\"><img decoding=\"async\" class=\"aligncenter size-full wp-image-2135 lazyload\" data-src=\"http:\/\/data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-5.png\" alt=\"Create-a-dataset-5\" width=\"798\" height=\"489\" data-srcset=\"https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-5.png 798w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-5-300x184.png 300w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-5-768x471.png 768w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Create-a-dataset-5-90x55.png 90w\" data-sizes=\"auto, (max-width: 798px) 100vw, 798px\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" style=\"--smush-placeholder-width: 798px; --smush-placeholder-aspect-ratio: 798\/489;\" \/><\/a><\/p>\n<p style=\"text-align: justify;\">I named the resultant dataset \u201cHashtag Analysis\u201d, as shown in the screen shot above. Now it\u2019s time to start a data exploration using Watson\u2019s Analytics \u201cExplore\u201d feature.<\/p>\n<h2 style=\"text-align: justify;\">Step 2: Start a Data Exploration Within Watson Analytics<\/h2>\n<p style=\"text-align: justify;\">After selecting \u201cHashtag Analysis\u201d as the dataset to explore, I was taken to the screen shown below.<\/p>\n<p style=\"text-align: justify;\"><a href=\"http:\/\/data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Analyze-a-dataset.png\"><img decoding=\"async\" class=\"aligncenter size-full wp-image-2138 lazyload\" data-src=\"http:\/\/data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Analyze-a-dataset.png\" alt=\"Analyze-a-dataset\" width=\"800\" height=\"495\" data-srcset=\"https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Analyze-a-dataset.png 800w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Analyze-a-dataset-300x186.png 300w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Analyze-a-dataset-768x475.png 768w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Analyze-a-dataset-90x56.png 90w\" data-sizes=\"auto, (max-width: 800px) 100vw, 800px\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" style=\"--smush-placeholder-width: 800px; --smush-placeholder-aspect-ratio: 800\/495;\" \/><\/a><\/p>\n<p style=\"text-align: justify;\">This is a \u201cExplore\u201d feature homepage. As you can see, Watson Analytics has already suggested some relationships that we might be interested in exploring from within the Hashtag Analysis dataset.<\/p>\n<p style=\"text-align: justify;\">We\u2019re going to explore our own custom relationship &#8211; &#8211; \u201c<strong>What is the breakdown of Retweet count by matching hashtag?<\/strong>\u201d.<\/p>\n<p style=\"text-align: justify;\"><a href=\"http:\/\/data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/RTs-by-Hashtags.png\"><img decoding=\"async\" class=\"aligncenter size-full wp-image-2136 lazyload\" data-src=\"http:\/\/data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/RTs-by-Hashtags.png\" alt=\"RTs by Hashtags\" width=\"1920\" height=\"943\" data-srcset=\"https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/RTs-by-Hashtags.png 1920w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/RTs-by-Hashtags-300x147.png 300w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/RTs-by-Hashtags-768x377.png 768w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/RTs-by-Hashtags-1024x503.png 1024w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/RTs-by-Hashtags-90x44.png 90w\" data-sizes=\"auto, (max-width: 1920px) 100vw, 1920px\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" style=\"--smush-placeholder-width: 1920px; --smush-placeholder-aspect-ratio: 1920\/943;\" \/><\/a><\/p>\n<p style=\"text-align: justify;\">Ok, so\u2026 let\u2019s look at what we\u2019ve got here. Watson Analytics has gone in to Twitter and pulled all the tweets that were tweeted last month that contained matching hashtags for the hashtags I queried. Based on the data that Watson Analytics queried, it looks like \u2026 well, if my goal is to use hashtags that are going to garner me the largest number of retweets (in other words, if I want to get the broadest reach), then I may want to use the following hashtags:<\/p>\n<ul style=\"text-align: justify;\">\n<li>#DataAnalytics<\/li>\n<li>#Analytics<\/li>\n<li>#DataScience<\/li>\n<\/ul>\n<p style=\"text-align: justify;\">Those are getting retweeted slightly more frequently than tweets with #BigData, #Machine Learning, and #Algorithms. Of course, there are competing factors that would need to be considered before making any substantive conclusions.<\/p>\n<p style=\"text-align: justify;\">Let\u2019s see what else Watson Analytics can tell us here\u2026 The screen below shows results from an exploration of \u201cthe number of Tweets for each Matching Hashtag\u201d.<\/p>\n<p style=\"text-align: justify;\"><a href=\"http:\/\/data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Tweets-by-Hashtags.png\"><img decoding=\"async\" class=\"aligncenter size-full wp-image-2137 lazyload\" data-src=\"http:\/\/data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Tweets-by-Hashtags.png\" alt=\"Tweets by Hashtags\" width=\"1916\" height=\"941\" data-srcset=\"https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Tweets-by-Hashtags.png 1916w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Tweets-by-Hashtags-300x147.png 300w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Tweets-by-Hashtags-768x377.png 768w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Tweets-by-Hashtags-1024x503.png 1024w, https:\/\/www.data-mania.com\/blog\/wp-content\/uploads\/2016\/05\/Tweets-by-Hashtags-90x44.png 90w\" data-sizes=\"auto, (max-width: 1916px) 100vw, 1916px\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" style=\"--smush-placeholder-width: 1916px; --smush-placeholder-aspect-ratio: 1916\/941;\" \/><\/a><\/p>\n<p style=\"text-align: justify;\">From this bubble chart shown above, we can clearly see that \u201cBig Data\u201d is the most frequently tweeted hashtag among the set I entered, followed by #Analytics, and then #DataScience. This data visualization helps me understand where the conversation is happening on Twitter.<\/p>\n<p style=\"text-align: justify;\">But, what are these other hashtags that are showing up? Those hashtags were not in my query! Well, it appears that those are co-related hashtags. By that I mean, those are hashtags that were found within tweets that did have a match for the hashtags I queried.<\/p>\n<p style=\"text-align: justify;\">Very cool!! These can give me some insights into other hashtags that are being frequently tweeted in the big data and analytics tweet streams. Should I update my Twitter hashtag strategy given these new insights? Perhaps \ud83d\ude42<\/p>\n<p style=\"text-align: justify;\">Since this is just a quick demonstration, I am not going to investigate further. But as you can see, even spending just a few minutes in Watson Analytics to create this demo has provided me additional value \u2013 I now have some evidence that I could use if I wanted to re-optimize my Twitter hashtag strategy. By looking at this second data visualization, I have put together a preliminary idea for hashtags I should reference to help make sure that my tweets make it into the Twitter conversation stream.<\/p>\n<p style=\"text-align: justify;\">Based on a very fast data exploration in Watson Analytics, I have surmised that I\u2019d do well by adding these hashtags into my tweets:<\/p>\n<ul style=\"text-align: justify;\">\n<li>#opines<\/li>\n<li>#opendata<\/li>\n<li>#nosql<\/li>\n<li>#bi<\/li>\n<li>#data<\/li>\n<li>#iot<\/li>\n<li>#hadoop<\/li>\n<li>#dataviz<\/li>\n<li>#googleanalytics<\/li>\n<li>#rstats<\/li>\n<li>#deeplearning<\/li>\n<li>#datawarehousing<\/li>\n<li>#dataliteracy<\/li>\n<\/ul>\n<p style=\"text-align: justify;\">But, no need to take my word for it. <a href=\"https:\/\/watson.analytics.ibmcloud.com\/product\" target=\"_blank\" rel=\"noopener\">Go visit Watson Analytics<\/a> and see what data insights you can discover for yourself.<\/p>\n<h2 style=\"text-align: justify;\">Want to Learn More About Analytics-As-A-Service?<\/h2>\n<p style=\"text-align: justify;\">This brings us to the end of our series on Analytics-as-a-Service. If you want to learn more on analytics-as-a-service though, or predictive analytics, then I recommend you to take a look at what you can find in Eric Siegel\u2019s book\u00a0<a href=\"http:\/\/34.gs\/6afw\" target=\"_blank\" rel=\"noopener\">Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die<\/a>. In its pages, you\u2019ll find plenty of stories and examples of how analytics are being used to revolutionize and redesign how business is successfully conducted in the modern world.<\/p>\n<hr\/>\n<p><em>Want a clean, repeatable system for measuring B2B growth? Get the free <a href=\"https:\/\/www.data-mania.com\/growth-metrics-os-email-course\/\"><strong>Growth Metrics OS<\/strong><\/a> \u2014 a 6-day email course for technical founders and operators who want to measure growth and make better decisions.<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>For our last installment in this 3-part series on analytics-as-a-service, I\u2019m going to provide you a quick and dirty demonstration of how to use Watson Analytics to analyze hashtag data from the Twitter social network. Step 1: Log-in to Watson Analytics and Add Your Data Once you get inside of Watson Analytics, you\u2019re going to [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":2139,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_links_to":"","_links_to_target":""},"categories":[582],"tags":[239,241,238],"class_list":["post-2130","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-startups","tag-analytics-as-a-service","tag-twitter-data-analysis","tag-watson-analytics"],"_links":{"self":[{"href":"https:\/\/www.data-mania.com\/blog\/wp-json\/wp\/v2\/posts\/2130","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.data-mania.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.data-mania.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.data-mania.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.data-mania.com\/blog\/wp-json\/wp\/v2\/comments?post=2130"}],"version-history":[{"count":1,"href":"https:\/\/www.data-mania.com\/blog\/wp-json\/wp\/v2\/posts\/2130\/revisions"}],"predecessor-version":[{"id":20379,"href":"https:\/\/www.data-mania.com\/blog\/wp-json\/wp\/v2\/posts\/2130\/revisions\/20379"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.data-mania.com\/blog\/wp-json\/wp\/v2\/media\/2139"}],"wp:attachment":[{"href":"https:\/\/www.data-mania.com\/blog\/wp-json\/wp\/v2\/media?parent=2130"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.data-mania.com\/blog\/wp-json\/wp\/v2\/categories?post=2130"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.data-mania.com\/blog\/wp-json\/wp\/v2\/tags?post=2130"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}