Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Sample of depressive-indicative phrases collected from tweets.

More »

Table 1 Expand

Fig 1.

The age distribution for depressed and control users in ground-truth dataset.

More »

Fig 1 Expand

Fig 2.

Gender and depressive behavior association (Chi-square test: Color-code: (blue:Association), (red: Repulsion), size: Amount of each cell’s contribution).

More »

Fig 2 Expand

Table 2.

Facial presence comparison in profile/posted images for depressed and control users—*** alpha = 0.05.

More »

Table 2 Expand

Table 3.

Statistics of processed shared/profile images.

More »

Table 3 Expand

Fig 3.

The Pearson correlation between the average emotions derived from facial expressions through the shared images and emotions from textual content for depressed-(a) and control users-(b).

Pairs without statistically significant correlation are crossed (p-value <0.05).

More »

Fig 3 Expand

Table 4.

Statistical significance (t-statistic) of the mean of salient features for both depressed and control classes—** alpha = 0.05, *** alpha = 0.05/223.

More »

Table 4 Expand

Table 5.

Statistical significance test of linguistic patterns/visual attributes for different age groups with one-way ANOVA, *** alpha = 0.001, ** alpha = 0.01.

More »

Table 5 Expand

Fig 4.

Characterizing linguistic patterns in two aspects: Depressive-behavior and age distribution.

More »

Fig 4 Expand

Table 6.

Age Prediction performance from visual and textual content for different age group(years old).

More »

Table 6 Expand

Table 7.

Facial presentation distribution for different age group(in years old) in profile and media.

More »

Table 7 Expand

Table 8.

Gender prediction performance through visual and textual content.

More »

Table 8 Expand

Fig 5.

Ranking features obtained from different modalities with an ensemble algorithm.

More »

Fig 5 Expand

Fig 6.

The explanation of the log-odds prediction of outcome (0.31) for a sample user (y-axis shows the outcome probability (depressed or control), the bar labels indicate the log-odds impact of each feature).

More »

Fig 6 Expand

Table 9.

Model’s performance for depressed user identification in Twitter using different data modalities.

More »

Table 9 Expand

Fig 7.

Word usage difference of likely vulnerable individuals versus random profiles.

More »

Fig 7 Expand