Extracting word embedding representation

We will start this section with an example to facilitate understanding. Suppose you are assigned to create the matching algorithm for a new dating service. This algorithm must identify people with similar characteristics and propose candidate profiles. Upon registering to the system, each user is asked a series of questions crafted to assess the five personality traits. The Big Five is a taxonomy for human personality and psyche. It includes extraversion, agreeableness, openness, conscientiousness, and neuroticism. Based on their answer, each user receives a score (percentage) for each trait according to the grayscale values of Figure 3.19:

Figure 3.19 – Grayscale values that signify the intensity of a characteristic

Figure 3.20 illustrates how we can visualize the users of the platform with a personalized grayscale vector that consists of five elements:

Figure 3.20 – Grayscale...