Response Needed for Post #1 below:
The company I have chosen and researched is Google. The mega-giant of it’s industry is a champion of data mining. With a platform which highly supports these tools, Google is able to gather information for nearly any platform they desire. In this situation, we are attempting to understand how they use text mining. Text mining is the action of gathering large amounts of data through text, or key words for example. Natural Language Processing (NLP) allows for this to occur. Computers are able to read and return information involving natural languages such as English using this tool. An example of how Google has used text mining, actually coincides well with our current state in the world. Although this was related to the common flu, Google partnered with the CDC to attempt to identify outbreaks as they are occurring. Using historical data from the CDC, Google compared search term queries against geographical areas that were known to have had flu outbreaks. Google found spikes in certain search terms where flu outbreaks occurred and identified forty-five terms that were strongly correlated with the outbreak of flu (Peterson, 2016). By searching specific text and search terms, Google is able to assist the CDC in identifying these key areas.
Web mining is also another tool that Google utilizes. Web mining is the act of gathering data from the world wide web. This category is slightly more broad, as you can search more categories of data such as search queries, text, URL’s, etc. Relating back to the situation involving the CDC, this falls under text mining as well as web mining. They are searching for text and specific searches but they are doing so throughout the web. This can allow Google to reach out into these areas that pose a great risk during the flu season. It is interesting to reflect as well on what other things this could help prevent, robberies, suicide, and even murder’s. It acts similarly to the movie, The Minority Report.
Response needed for post #2 below:
Chapter 21 of this week’s reading assignment discusses Big Data and the various methods and processes of collecting data. Text mining involves analytics and collection of information from written text of various applications and webpages such as Facebook, news articles, emails (Learning Hub, 2019). Similarly connected, web mining involves scanning and analyzing data from web portal and pages.
The large healthcare facility I work for uses both of these applications in its process of collecting data for both research as well as for process improvement. In terms of the clinical practice, the organization currently uses applications such as PerfectServe, which enables physicians and staff to communicate back and forth through a web portal and text like process. These communications are monitored and time stamped, with the data used to verify timeliness of communication. This is especially important in terms of critical lab values or in the events of patient instability/decline.
In the past two years the organization I work for has focused on connecting with both patients and staff in new, innovative including the use of Twitter and the company web portal. The company has tried to increase traffic and visits to the company web portal by posting weekly news articles and video messages as well as sending out emails to staff with links to the web portal. By using web mining, the organization is able to measure the amount of ‘foot traffic’ to the company’s web page and to a degree measure how effective its communication strategy is. As recent research indicates, the use of internet based and connected technology will increase and presents an opportunity for hospitals to use this technology to directly impact the patient experience, including reducing ER wait times (Millman, 2015).