Digital Bacon

[...] while talking to people about Thinkudo Enlighten. It regards the misunderstanding between Text Analytics and Machine (automated) Translation. More than once people've asked "How did you do the [...]

[...] In my last post, I introduced the segmentation challenges of Chinese for text analytics. For this post, I will describe the difficulties on the term level because of homographs. [...]

[...] retrieval technologies. This experience ultimately lead me to found my startup in text analytics for social contents. After this long loop with information retrieval, recommendation [...]

[...] Natural Language Processing (NLP) libraries including NLTK and pattern. For some, NLP, or text analytics, need no introduction nor justification. For those new to it, NLP is the field which studies [...]

[...] emotions? Within psychology, there's been long discussions and many studies to identify the basic emotions which all others are built from. Despite the variations within this ongoing field, between 6 [...]

[...] and Devillers used the Big Six (widely adapted six emotions identified by Paul Ekman) as the basic emotions to classify, but also used more complex emotions including relief and anxiety as well. When [...]

[...] within every person, regardless of their cultural backgrounds. You can read more about these basic emotions on my previous post. This shared platform is what makes communication in person easier than [...]

As the Chinese consumer market takes the center stage in the world economy, the rush to adapt business tools for the Chinese market is equally as fren [...]

Do you know what's the most used term in the Chinese language according to our social media sources? If you've read the title, you can probably guess. [...]

In my last post, I introduced the segmentation challenges of Chinese for text analytics. For this post, I will describe the difficulties on the t [...]

[...] exist a margin of error greater than 0. Therefore, when translated text is used as training data for an NLP algorithm, the translation's margin of error is added into the engine. Even [...]

[...] is closer to a training point. This holistic prediction allow engineers to account for how the training data relates to the prediction depending their distances are. On the flip side of the coin, the [...]

[...] Cloudant variant, a lot lately. It's been a great experience so far. However, as any database technology, as the data size grows, the bad practices and gotchas become more evident. We had to deal [...]

[...] . Meanwhile, there are numerous powerful mathmatical, statistical techniques within the Data Mining community that cannot be used because it is semantics free. Vector Space Model (VSM) is a powerful [...]

[...] the result set while using the latter elements to store the static values. In our example of location data, we have geographical coordinates we want to return as well as how often the location was [...]

[...] . These functions required and assume all the raw values emitted are numeric. If you keep static data, such as coordinates or temperature, these functions will apply the operations on to those [...]

[...] the data is of poor quality, then the result cannot be trusted. It is the same reason why, as data scientists, we spend more time observing and cleaning the data than implementing the actual analysis [...]

[...] "second-best" solutions. Gaussian Process Guassian process is one of the latest regression techniques. Instead of creating a single function (using an optimized weight vector), it produce a [...]