How to check whether lip movement is significant using face landmarks in dlib?

I am trying to assess whether the lips of a person are moving too much
while the mouth is closed (to conclude they are chewing).

I try to assess the lip movement through landmarks (dlib) :

Inspired by the mouth example (
https://github.com/mauckc/mouth-open/blob/master/detect_open_mouth.py#L17),
and using it before the following function (as a primary condition for
telling the person is chewing), I wrote the following function:

def lips_aspect_ratio(shape):
    # grab the indexes of the facial landmarks for the lip
    (mStart, mEnd) = (61, 68)
    lip = shape[mStart:mEnd]
    print(len(lip))
    # compute the euclidean distances between the two sets of
    # vertical lip landmarks (x, y)-coordinates
    # to reach landmark 68 I need to get lib[7] not lip[6] (while I
get lip[7] I get IndexOutOfBoundError)
    A = dist.euclidean(lip[1], lip[6])  # 62, 68
    B = dist.euclidean(lip[3], lip[5])  # 64, 66

    # compute the euclidean distance between the horizontal
    # lip landmark (x, y)-coordinates
    C = dist.euclidean(lip[0], lip[4])  # 61, 65

    # compute the lip aspect ratio
    mar = (A + B) / (2.0 * C)

    # return the lip aspect ratio
    return mar


How to define an aspect ratio for the lips to conclude they are moving
significantly? Is the mentioned function able to tell whether the lips
are significantly moving while the mouth is closed?