How Companies Can Use Sentiment Analysis to Improve Their Business

If you have 1 to 10 articles, the most effective way to measure sentiment is to simply read them. But what happens if you have 50,000? This is where automated sentiment can provide some directional insight and set the tone for further analysis.

.. You should aim to uncover important phrases like “bad quality,” “crashes too often,” and “won’t start.” This can and should affect your product design, customer service, marketing messaging and social media outreach. Can you discover if there are particular influencers driving the negative conversation and do anything to reach out to them?

.. If you need to neutralize the mentions that hurt your brand the most, you should drill down into negative mentions, identify the content coming from the most influential people in your industry, understand how far each tweet traveled, and how many people were impacted by this content.

.. The Holy Grail of Social CRM is the ability to close the analytical loop between publicly expressed sentiment, engagement action, subsequent purchase intent, and ultimately, product purchase.

.. Because you now have a history on this person, and your system cross-references his/her social media profiles across several platforms, you are able to track this person’s affinity and sentiment towards your brand over time, monitor their purchase intent, and note their influence on others’ purchase decisions.

Big Data at College: Spotting Academic Trouble

Tools developed in-house and by a slew of companies now give administrators digital dashboards that can code students red or green to highlight who may be in academic trouble. Handsome “heat maps” — some powered by apps that update four times a day — can alert professors to students who may be cramming rather than keeping up. As part of a broader effort to measure the “campus engagement” of its students, Ball State University in Indiana goes so far as to monitor whether students are swiping in with their ID cards to campus-sponsored parties at the student center on Saturday nights.

Cyrus Vance Jr.’s ‘Moneyball’ Approach to Crime

But Vance’s most significant initiative, one that has been emulated in jurisdictions from Brooklyn to San Francisco, has been to transform, through the use of data, the way district attorneys fight crime. “The question I had when I came in was, Do we sit on our hands waiting for crime to tick up, or can we do something to drive crime lower?” Vance told me one afternoon in his eighth-floor office at the Criminal Courts Building in Lower Manhattan. “I wanted to develop what I call intelligence-driven prosecution.”

.. They asked police commanders to submit a list of each precinct’s 25 worst offenders — so-called crime drivers, whose “incapacitation by the criminal-justice system would have a positive impact on the community’s safety.” Seeded with these initial cases, the C.S.U. built a searchable database that now includes more than 9,000 chronic offenders, virtually all of whom have criminal records.

.. When someone in the Arrest Alert System is picked up, even on a minor charge or a parole violation, or is arrested in another borough, any interested prosecutor is automatically pinged with a detailed email. People outside the D.A.’s office like parole officers or police intelligence officers are often notified, too.

.. “There’s a reason murders in Manhattan went from 70 in 2010 to 29 so far this year,” Karen Friedman Agnifilo, former chief of the Trial Division, told me late last year. (In January, Vance promoted Friedman Agnifilo to the No. 2 job, chief assistant district attorney.) “We figured out who are the people driving crime in Manhattan, and for four years we focused on taking them out.”

.. Did the Manhattan D.A., they ask, really need to set up a two-year study with the Vera Institute of Justice to realize the criminal-justice system was plagued by racial bias? And in light of its entrenched inequities, aren’t databases and targeted intelligence-based prosecution especially problematic?

.. “When prosecutors begin to compile databases and start doing so-called ‘smart prosecutions,’ you have to ask who is getting in the databases, what are the criteria and where are the outside checks?” says Steven Zeidman, director of the criminal-defense clinic at the CUNY School of Law. “More than a thousand people are arrested in N.Y.C. each day, and the overwhelming and disproportionate number of them are people of color arrested for ‘broken windows’ type offenses like riding a bike on the sidewalk or jaywalking. I was in court with a kid arrested for jaywalking; the arresting officer was from the gang unit, and he stopped the kid because he was wearing a red shirt that, according to the police, happened to be a gang color. He wasn’t in a gang, but he’s probably now in a database.”

..  It’s very clear to our D.A. that we are overincarcerating, and we need to do something different. Jail is not an economically sustainable model. We need to know for whom jail is appropriate and whom it isn’t. That’s where data becomes very useful.”