# 5 Things To Do with a Data Set

Clustering

Like prediction and classification, understanding the way the data is organized can help us with analysis of data. One way to tease out the structure of the data is by examining clustering. Based on the patterns shown in the data, we can group individual observational units into distinct clusters. Clusters are defined so that observations within each cluster will have similar characteristics.  We can do further analysis of each group as well as comparing between groups. For example, marketers may want to know the customer segments to develop targeted marketing strategies. A cluster analysis will group customers so that people in the same customer segments tend to have similar needs but are different from those in other customer segments.  Some popular clustering methods are multi-dimensional scaling and latent class analysis.

Image source: http://www.dynamic-concepts.nl/en/segmentation/

Classification

The first step is constructing a classification system. The categories can be created based on either theories or observed statistical patterns such as those detected using clustering techniques. The next step is to identify the category or group to which a new observation belongs. For example, a new email can be put in the spam bin or non-spam bin based on the contents of the email. In statistics and machine learning, logistic regression, linear classifier, support vector machine and linear discriminant analysis are popular techniques used for classification problem.

Prediction

Predictive models can be built with the available data to tell you what is likely to happen. Predictive models assume either that a knowledge of past statistical patterning can be used to predict the future or the validity of some type of theoretical model.  For example, Netflix recommends movies to users based on the movies and shows which users have watched in the past.

Can we predict who will be the next president, Clinton or Trump? Yes, we can. Based on the polling data or candidates’ speeches, you can build a predictive model for the 2016 presidential election.  Nate Silver is well-known for the accuracy of his predictions of both political and sporting events. Here is his prediction model on the 2016 presidential election:

Source: http://projects.fivethirtyeight.com/2016-election-forecast/

Predictive modeling utilizes regression analysis, including linear regression, multiple regression and generalized linear models, as well as some machine learning algorithms, such as random forest tree and factor analysis.   Time series analysis can be used to forecast weather and the sales of a product of next season.

Anomaly Detection

Anomaly detection identifies unexpected or abnormal events. In the other words, we seek to find deviations from expected patterns. Detecting credit card fraud provides an example.  Credit card companies can analyze customers’ purchase behavior and history, so they can alert customers of possible fraud. Here are examples of popular anomaly detection techniques: k-nearest neighbor, neural network, support vector machine and cluster analysis.

Decision Making

One of the most common motivations for analyzing data is to drive better decision making. When a company needs to promote a new product, it can employ data analysis to set the price to maximize profit and avoid price wars with other competitors. Data analysis is so central to decision making that almost all analytic techniques – including not only the ones mentioned above but also geographical information systems, social network analysis, and qualitative analysis – can be applied.

You can leave the list at any time. Removal instructions are included in each message.

# Clinton vs. Trump on Immigration: What Do Their Official Websites Reveal?

On her website, Clinton provides positions on over thirty-five issues, while Trump lists positions on just thirteen issues, a number that has grown from a mere seven positions a month ago. Trump and Clinton’s stances on immigration differ dramatically. While the Trump campaign frames immigration as a source of tremendous economic turmoil and a gateway for crime into the United States, Clinton devotes much more of her rhetoric towards demonstrating compassion for immigrants.

Word Cloud: 30 Most Commonly Used Words in Clinton’s Position on Immigration

Word Cloud: The 30 Most Commonly Used Words in Trump’s Position on Immigration

After “immigration,” the most commonly used word on Clinton’s immigration webpage was “families” (16 uses), while for Trump  it was “illegal” (18 uses). Other common Trump words include: “visa,” “states,” officers,” “aliens,” and “ICE” (Immigration Customs Enforcement). All reflect his conceptualization of immigration as a legal issue that necessitates aggressive enforcement.

The immigration statement posted on Trump’s website has twelve references to the economy and seven references to crime. Simultaneously framing immigration as a cause for economic and criminal concern, Trump cited the “horrific crimes” border-crossing criminals have committed against Americans.

Screenshot of Donald Trump’s Immigration Reform Webpage

Trump attempts to strike fear in the hearts of everyday Americans by explicitly connecting unlawful immigration with infrequent and sensationalized violent crimes. His website graphically describes, “an illegal immigrant from Mexico, with a long arrest record, is charged with breaking into a 64 year old woman’s home [and] crushing her skull and eye sockets with a hammer.” He also links immigration to terroristic crime: “From the 9/11 hijackers, to the Boston Bombers, and many others, our immigration system is being used to attack us.”

For Trump immigration is a cause of economic anxieties for ordinary citizens.  He claims that “U.S. taxpayers have been asked to pick up hundreds of billions of healthcare costs, education costs, welfare costs, etc. Indeed the annual cost of free tax credits alone paid to illegal immigrants quadrupled to \$4.2 billion in 201. The effects on jobseekers have also been disastrous, and black Americans have been particularly harmed.”

Many of his policy plans tie the economy to immigration. Beneath a heading that reads “Jobs program for inner city youth,” Trump explains that under his administration, “The J-1 visa jobs program for foreign youth will be terminated and replaced with a resume bank for inner city youth provided to all corporate subscribers to the J-1 visa program.”

“Us Versus Them” provides a consistent theme. Trump’s platform states, “Real immigration reform puts the needs of working people first – not wealthy globetrotting donors,” once again emphasizing his economic concerns regarding immigration while appealing to working-class Americans. He assures voters that “We will not be taken advantage of anymore” by Mexico.

In contrast, Clinton’s position on immigration reform (listed under the “Justice and Equality” section of her issues webpage) uses pro-immigrant and pro-family rhetoric.

Screenshot of Hillary Clinton’s Immigration Reform Webpage

Unlike her opponent, Clinton does not use the word “illegal” a single time on her immigration webpage.  Notably, she does not use the politically correct alternative “undocumented” either.   Clinton asserts that Americans must “stay true to our fundamental American values; that we are a nation of immigrants, and we treat those who come to our country with dignity and respect—and that we embrace immigrants, not denigrate them.”

Clinton refers to immigration as a crime only once. She claims that: “Immigration enforcement must be humane, targeted, and effective,”  and that she will “focus resources on detaining and deporting those individuals who pose a violent threat to public safety.” While this part of the statement does frame some immigrants as “violent threats,” it positions most as law-abiding members of families.

In stark contrast to Trump, Clinton places a premium on showing compassion for immigrants who face difficult circumstances and emphasizes keeping families together as a top priority of her immigration policy.  Clinton states that she would “Do everything possible under the law to protect families.” She “will end family detention for parents and children who arrive at our border in desperate situations and close private immigrant detention centers,” and even ensure health care to all families including those of immigrants.

Clinton’s page includes words like “heartbreaking” and “sympathetic” to describe the cases of immigrants who do not enjoy full legal status and claims that her plan for immigration reform will “bring millions of hardworking people into the formal economy.”

You can leave the list at any time. Removal instructions are included in each message.

# Clinton vs. Trump: Who‘s Winning on Twitter?

An analysis of 3000 tweets sent by the Clinton and Trump campaigns between March and early September this year (2016) reveals stark differences in both content and social media exposure.

Up to September 2016, Trump boasted a number of 11.6 million Twitter followers compared to 8.86 million for Clinton. The average number of retweet for Trumps’ Twitter posts (5493) is also roughly twice as high as that from Clinton’s (2556).

Interestingly, as of July 2016, the number of daily tweets from Clinton’s account doubled to roughly 30 tweets daily while that same figure from Trump hovered around 12 tweets a day. These statistics suggest that Trump is gaining more engagement from Twitters’ users, even though Clinton is also fighting hard to gain presence in social media.

Tweets’ content analysis

Clearly, both candidates refer to each other consistently in their tweets. Clinton mentions Trump primarily in terms of his disrespect for generals, immigration policies, tax breaks for the wealthy and failure to release tax returns. Popular themes in Clinton’s tweets are “families”, “women” and “jobs”. She tends to use words that suggests the togetherness of the American community as well as a positive attitude towards good changes for America.

Similarly, Trump made many references to Clinton through his posts, although he tended to use her first name, rather than her last. The word “Hillary” or the phrase “Crooked Hillary” was mentioned 547 times. Common topics that Trump addresses include controversy around Clinton’s emails, media manipulation, and criticism towards Clinton’s policies on foreign affairs and immigration.

Interestingly, Trump refers to Democrats, like Bernie Sanders and Barack Obama, as well as Republicans like his former opponents Ted Cruz and Marco Rubio. Unlike Clinton, Trump tends to make a greater use of words with negative tones, which sketch a pretty bleak portrait of the  U.S. , perhaps to make the case for the need to, as his campaign slogan phrases it, “Make American great again”.

Who do they talk to?

In her tweets, Clinton frequently mentions @realDonaldTrump, but Trump does not seem to tag Clinton or mention her Twitter handle even though his Tweets mention her name consistently. Clinton seems to employ the strategy of engaging with and directly mentioning her opponent’s Twitter account, whereas Trump chooses to simply ignore his rival. It remains to be seen which strategy is more effective in this presidential election.While Clinton tends to mention Twitter users who are figures of her political party – @BillClinton for example, Trump referred to various right-wing media shows and channels – such as @FoxNews and @MegynKelly. Interestingly, Trump’s posts with mentions have on average 4 times the number of retweets as those without mention. Clinton’s posts with mentions have a 3 times higher number of retweets. Thus, mentions appear to increase the likelihood of retweets. Given that the average number of retweets for Trump’s posts is greater than that of Clinton’s, it seems like Trump’s way of using mentions may help him gain more attention from Twitter’s user community, although there may be other explanations as well.

You can leave the list at any time. Removal instructions are included in each message.

# 2016 RNC vs. DNC Convention: Night and Day

Using Nvivo, a text-analysis software, DASIL compared Clinton and Trump’s convention speeches to demonstrate the stark contrast between the two presidential candidates. The previous post briefly examined key themes in each candidate’s address using word clouds. This analysis expands on the previous post with a more in-depth comparison of the two candidates’ approaches to the following themes:

Immigration:

Table demonstrating the frequency of mention of the word “immigration” or “immigrant(s)” by count

Table demonstrating the frequency of mention of the word “immigration” or “immigrant(s)” as percentage of total number of words in each speech.

In Donald Trump’s speech, 10 out of 13 times in which “immigration” or “immigrant(s)” is mentioned, it’s accompanied by words with negative connotation such as “illegal”, “radical”, “dangerous”, or “uncontrolled”. According to Trump, immigration is deemed the cause of poverty, violence, drug issues, unemployment, and terrorism.

In contrast, Clinton presented herself as an advocate for comprehensive immigration integration, which is clearly demonstrated in her convention speech: 2 out of 4 times Clinton mentioned these words, “immigration” or “immigrant(s)” is accompanied by positive words and phrases. She described immigrants as “contributing to our economy” and “hardworking”.

Jobs:

Table demonstrating the frequency of mention of the word “job(s)” by count

Table demonstrating the frequency of mention of the word “job(s)” as percentage of total number of words in each speech.

Given the long-standing lag in job growth, outlining a vision for jobs creation and income gains is among the top priorities on the two candidates’ agenda. As mentioned in a previous post, Trump held a pessimistic outlook on the American economy: 4 out of 13 “job(s)” words mentioned by Trump are surrounded by words with negative connotation. The Republican nominee talked about the prospect of jobs and wages reduction with Clinton administration and consider regulation “one of the greatest job-killers of them all.”

On the other hand, Hillary Clinton chose to deliver a more hopeful view of the matter. She highlighted the prospect of good-paying jobs and the effectiveness of her policy in job creation. None of out of 18 times she touched upon the subject of employment did she make a negative remark on the issue.

Patriotism

Table demonstrating the frequency of mention of the word “America(ns)” by count and as percentage of total word count

The two presidential candidates frequently mentioned “America(ns)” in their speech, and the word clouds visualize the frequency of the use of these words between Clinton and Trump. In fact, Trump mentioned “America(ns) almost three times as often as Clinton did – both in terms of count (number of times “America(ns)” is mentioned) and percentage (number of times “America(ns)” is mentioned as a percentage of total word count).

Even though both Trump and Clinton embraced patriotism in their convention speeches, they did so in two strikingly different ways. The Republican Party and its presidential nominee portrayed America as a country under attack by all things foreign; the country is in a dark place and Trump is the one to “make America great again.” In contrast to Trump’s nationalism, Clinton talks about American in optimistic tones, emphasizing the family values – faith, community, and togetherness – that middle-class Americans adhere to.

You can leave the list at any time. Removal instructions are included in each message.

# 2016 U.S. Presidential Race: Do Convention Speeches Predict the Winner?

After the Republican and Democratic Conventions in July, the 2016 U.S. presidential race is on between Democrat Hillary Clinton, who is making history as the first female presidential nominee from one of the two major political parties, and Republican Donald Trump, the contentious and provocative New York billionaire. The race for the White House this year is undoubtedly one of the most memorable events in the history of American politics, partly because of the stark contrast between the two candidates, from their political and economic agenda to their appeal to voters. Using Nvivo, a text-analysis software, DASIL compared Clinton and Trump’s acceptance speeches at their respective party conventions to further demonstrate these differences.

Main theme and important issues

30 most frequent words in Donald Trump’s speech

Looking at the 30 most frequent words in Trump’s speech, we can see that the main issues mentioned by the Republican candidate are immigration, national security, and public safety. The most common words in the speech include “violence”, “immigration”, “protect”, “border”, “laws”, “jobs”, and “violence”, highlighting a dark portrait of the current state of America. Trump strongly emphasized that much must be changed in order to fix these issues, and that he, rather than a Democratic leader, will change this grim outcome by restoring law and order.

30 most frequent words in Hillary Clinton’s speech

Clinton, on the other hand, gave a more optimistic and upbeat speech. While acknowledging the current issues facing America and the work needed to be done, Clinton also highlighted the strengths that the nation brings to overcome these challenges. Some of the most frequent words in her speech are “family”, “people”, “works”, “jobs” and “together”, hinting at some issues that the Democratic presidential candidate wants to tackle. At the same time, these words center around the notion of inclusivity and staying united, which offers stark contrast to Trump’s anti-immigration stance, isolationism, and Americanism.

“We” versus “I”

Using Nvivo, DASIL also compares how often the two presidential candidates used “we” words – such as we, our, ours, and ourselves – versus “I” words – such as I, me, my, mine, and myself in their convention speeches.

For every time Clinton said “I”, she said “we” 1.83 times, while her Republican opponent said “we” only 1.5 times for each “I”. With a 1.50 “we”-to-“I” ratio, Trump delivered a more self-focused convention speech than his Democratic rival Hillary Clinton, whose speech has a “we”-to-“I” ratio of 1.83. The difference in use of “we” versus “I” words between the two candidates reveals much about their speaking styles, personalities, and even chances of winning the election. A Bloomberg Politics study of convention speeches dating back to 1976 finds that the public tend to favor candidates who use more “we” words relative to “I” words. In nine out of 10 elections since 1976, the general election winners achieved a higher “we”-to-”I”-word score compared to his opponent [Bloomberg]

Bloomberg points out that “we” words inspire confidence in others and also reflect the speaker’s self-confidence, which is a key quality in good leadership. Clinton’s “we”-to-“I” victory over Trump in her convention speech suggests that she’s in the lead position to win in November. Trump’s speaking style is more personal; furthermore, his I-word usage reveals feelings of insecurity, perhaps due to a lack of political background and experience on political issues.