One Wordcloud A Day

Today Kobe Bryant announced his retirement. Kobe is a controversial player for so many reasons and in particular because of the sexual assault case (https://en.wikipedia.org/wiki/Kobe_Bryant_sexual_assault_case). If I have to look beyond all this and just consider his game, I really like Kobe as a player. But unfortunately I can't look beyond the other things :( Nonetheless, Kobe is one of the greatest NBA players, few would disagree with that. I find it interesting that not a lot of positive words were associated with his announcement today (on Twitter at least). I see "MVP", "legendary", and "greatest" showing up but at a much lower frequency than "Lakers", "retire", and "NBA". The sentiment was neutral for the most part but positive bar is also quite tall.

Today's hashtag is TrackOfTheDay, which is clearly about music. I wasn't sure whether this is a promoted hashtag but after looking at the wordcloud I know it was. Shazam is showing up so many times with The Vamps Band, it is a clear indication that this was not organic. Not an issue for me! It shows that worcloud is powerful enough to grab such patterns. The sentiment is highly positive. I am not surprised.

Today when I looked at the trending topics, #PlannedParenthood was among them. But this was not for some nasty thing Donald Trump (or other Republican nominees) said about them. Instead it was for the tragic shooting at their premises in Colorado. http://www.wsj.com/articles/active-shooter-reported-at-planned-parenthood-clinic-in-colorado-1448654443 Three people died in the attack but the alleged shooter was arrested. The wordcloud clearly shows the shooting association with Planned Parenthood although sometimes "prolife" pops up. Presumably the shooter was white so that word also shows up frequently. The sentiment was polarized. This is likely due to the negative words surrounding shooting and positive words surrounding Planned Parenthood and victims (I hope so!)

Macy's is trending! I don't get to use a lot of brand related hashtags so I decided to take this opportunity. Turns out that Macy's Parade hashtag was overwhelmed by the avocado guys, at least when I downloaded the tweets. This is what I like to call hashtag hijacking. So the equally trending hashtag is #AvosToNYC which was coined by the Twitter account @AvosfromMexico The sentiment is bimodal, mixed. I guess many people loved this but several others hated it!

Captain America: Civil War trailer is trending right now! I decided to use this for the wordcloud today using "Civil War" as the search query. For the wordcloud I deleted the obvious words such as "trailer" and the title of the movie. Here is the wordcloud, which looks quite uninformative to me. I don't know why f-word shows up here although less frequently The sentiment is overly positive. No wonder here. People like this guy and they liked the trailer as well!

Yesterday I couldn't get a lot of tweets with the hashtag #RussianPlane. I tried again today with a non hashtag keyword "Russian" and here is what I got: And here is the sentiment, which is way more negative compared to yesterday's graph

Wow this has been a long break since the last post! I have been traveling a lot and so didn't always get time to update the blog. Anyway, I am now in Singapore and hope to update the blog daily. So right now the news that's unfolding is the downing of Russian plane by Turkey. As a result, #RussianPlane has just started trending. I didn't get a lot of Tweets to analyze and the wordcloud is kind of obvious. But for some reason I see Egypt's name popping up a few times. On the positive side I didn't see any reference to WW3! The sentiment around this hashtag is obviously negative.

Today ISIS was trending and I decided to make a wordcloud from that rather than using any trending hashtag. The wordcloud shows context-specific words, obviously linking to Paris attacks. But there are some other interesting words patterns too. I thought this was very interesting. In particular the news that Anonymous is taking on ISIS has struck a cord with people. Also, there is some talk about Obama. Perhaps calling for him to fight with ISIS with more intensity? Putin's name shows up a bit as well. Interestingly only these two world leaders show up often. French president Hollandes is curiously absent! The sentiment is very negative, as expected.

Today I downloaded tweets for the show #XFactor as this hastag was sort of trending. I didn't want to get one more sports related hashtag. I wasn't too hopeful about this because I thought the hashtag wasn't necessarily trending. But I was wrong! I could quickly get 100K tweets and to my surprise I found that the wordcloud was dominated by certain words ("factor" was sort of obvious but I didn't anticipate it). This is an indication of a lot of retweets. So for me now is the time to adjust the code to remove retweets. But I am not sure whether to remove them because that will mean that we put the same weight on all the tweets not taking into account the popularity (through retweets in this case. I haven't looked into the favorite tweets so far). Anyway, here is the wordcoud. The word "Olly" shows up because it's the name of the presenter of the show and it seems that he screwed up by telling a contestant the outcome before the results were

Today was a dark day. So many innocent people died in Paris attacks. I decided to make a wordcloud of #ParisAttacks, the most trending hashtag as of right now. Ususally I download 100K tweets and then clean them up. There was some problem with my internet today so I had time to download on 50K. Anyways, that's a big number right there. There are some very interesting patterns that are popping out. Lights is the most frequent word followed by "world." ANy idea why? I couldn't figure out yet. Another hashtag that was trending earlier #PrayForParis was also used quite often with this hashtag. Looks like people have concluded that it was ISIS behind the attacks. Luckily xenophobic comments seem to be limited because the word "muslims" is now as frequent as it would be if the comments were racist. The sentiment graph below also shows a similar pattern. And here is the sentiment graph. Nothing much groundbreaking here. The positive sentiment is stronge

Today a funny hashtag was trending so I decided to use it. Most of the hashtags I have explored so far have been for politics or music. So this presents some change. Ex ante I expected that there will be a weird wordcloud because there may not be any common theme here. Well it turns out that I was almost right. There is the word "midnight" that shows up a lot in the tweets with this hashtag. As it turns out midnight is an account name that shows up with this hashtag as this tweet suggests: Revolutionary Hashtag War #InternetThePast @midnight — John Cioch (@John_Cioch) November 13, 2015 Midnight is a "late night game show thing hosted on Comedy Central" But apart from that other words look more or less uniformly distributed. The words "pointsme" also shows up slightly more frequently compared to the other words but I don't know what that is. The sentiment  for the hashtag was highly polarized. I had no idea about this going in but this is

Sorry for the break over the last few days. I was in Shanghai and all Google services are blocked there including Blogger.com. Also, Twitter is blocked so I couldn't get any tweets to analyze. Now that I am back in Singapore, here is the wordcloud for today. Trump is at the center of the GOP debate! He is killing it (on Twitter at least). Interestingly Ted Cruz and Rubio are now showing up. Fiorina and Carson get a few mentions. But look at Jeb Bush! Can you even spot him here? The sentiment is as expected. Clearly way more positive than negative.

Today when I checked the trending hashtags, this one popped up. It came from Justin Bieber's Twitter account so his name appears quite often. Anyway, the wordcloud is here   The sentiment graph is here. It's quite polarized and there are not many neutral tweets!  

Today's hashtag was #CMA awards (Country Music Association awards). I downloaded the tweets from Cambodia but then couldn't get time to complete the analysis. Anyway, I am not back in Singapore and so here is today's wordcloud. Guess who is trending with CMA awards? It's Justine Timberlake. Miranada Lambert also appears several times. No wonder the word "country" appears often (I should have removed it from the wordcloud)   The sentiment was quite positive. This is a good thing for the CMA awards, right?  

I am in Cambodia right now for a student project. Yesterday was too busy so I didn't have time to download any tweets. I collected a few tweets today and here is the analysis! Today's hashtag was #BeingMaryJane. I had no idea about this show and so it was good to know that it existed and a lot people like it. You can read more about the show here: https://en.wikipedia.org/wiki/Being_Mary_Jane Anyway, the wordcloud is here. Maybe you will know more about this if you are already a fan of the show! And here is the sentiment graph. The sentiment is positive but not a lot.

Jeb Bush did it. Finally, I have a sentiment graph where the negativity is more than the positivity! Some background merits a mention. Jeb Bush is running for the GOP primaries and his campagn manager thought that it would be a good idea to launch #JebCanFixIt hashtag. It just so happened that it wasn't a good idea. The hashtag was provocative and couldn't be easily hijacked. That's exactly what happened. People started making fun of Jeb Bush by using this hashtag. Note that one doesn't have any control over how people use the hashtag. This is a good lesson for all the social media managers! If you want to read more about this check out this news story: http://observer.com/2015/11/internet-trolls-hijack-jeb-can-fix-it-campaign-possibly-ending-bushs-run-for-good/ Well, there is nothing much interesting in the wordcloud itself except that Vernon shows up. He is in the news right now but again I don't know why he would appear with this hashtag! "Funny"

Today is Justin Bieber's day! The hashtag for today is #IllShowYou, which is Justin's latest single. I found this audio on YouTube: https://www.youtube.com/watch?v=Q5gYDOmERU8 The wordcloud is a bit crappy because there are long words that are the leftover hyperlinks. So they really don't mean anything. I guess these links were shared a lot on Twitter and my code didn't do a good job of removing them. Anyway, I will adapt my code soon to fix this. I thought it was interesting that Skrillex appeared many times in the tweets with this hashtag. He is in the news because of some Twitter fight he got into with Deadmau5 (omg, what the heck is happening to me?) but I don't know why that should relate to this hashtag. The words "purpose" and "get" show up several times as well. I guess "get" is for getting the song but I might be wrong there. As "preorder" is also showing a few times, "get" is likely to mean buy. Ju

I had no idea what this hashtag is until I started checking out the tweets. To all the fans, here is goes! And of course, the sentiment analysis. Not as positive as I thought it would be, though.