Text Mining and Machine Learning Sample Clauses

Text Mining and Machine Learning. Text mining is an umbrella term describing a range of techniques that allow soft- ware to extract useful information from text collections (Xxxxxxx & Xxx Xxxxx, 2014; Xxxxxxx & Xxxxxx, 2007). These techniques are not new, with the first man- ual Text Mining processes being done in the 1980s (Xxxxxxxx & Xxxxxxxx, 1984) and more automated computer aided Text Mining emerging in the 1990s (x.x. Xxxxxxx & Xxxxx, 1995). Recently, Text Mining has received renewed attention due to the emergence of the ‘Big Data’ and data mining trend, and Text Mining applications have been steadily increasing in number. Typical Text Mining tasks include text categorisation, text clustering, sentiment analysis, translation, doc- ument summarisation and NER (Xxxxxxx & Xxx Xxxxx, 2014). NER is the task we focus on in this study, and is further described in the next section. Machine learning is often used to perform Text Mining tasks, as opposed to rule-based approaches that were popular originally. Machine learning can be broadly defined as “computational methods using experience to improve perfor- xxxxx or to make accurate predictions” (Xxxxx et al., 2013, p. 1), where expe- rience refers to past information available to the learning algorithm, also called