Function modality

pattern/text/en/modality.py:376–424

Returns the sentence's modality as a weight between -1.0 and +1.0. Currently, the only type implemented is EPISTEMIC. Epistemic modality is used to express possibility (i.e. how truthful is what is being said).

(sentence, type=EPISTEMIC)

}

def modality(sentence, type=EPISTEMIC):
    """ Returns the sentence's modality as a weight between -1.0 and +1.0.
        Currently, the only type implemented is EPISTEMIC.
        Epistemic modality is used to express possibility (i.e. how truthful is what is being said).
    """
    S, n, m = sentence, 0.0, 0
    if not (hasattr(S, "words") and hasattr(S, "parse_token")):
        raise TypeError, "%s object is not a parsed Sentence" % repr(S.__class__.__name__)
    if type == EPISTEMIC:
        r = S.string.rstrip(" .!")
        for k, v in epistemic_weaseling.items():
            for phrase in v:
                if phrase in r:
                    n += k
                    m += 2
        for i, w in enumerate(S.words):
            for type, dict, weight in (
              (  "MD", epistemic_MD, 4), 
              (  "VB", epistemic_VB, 2), 
              (  "RB", epistemic_RB, 2), 
              (  "JJ", epistemic_JJ, 1),
              (  "NN", epistemic_NN, 1),
              (  "CC", epistemic_CC_DT_IN, 1),
              (  "DT", epistemic_CC_DT_IN, 1),
              (  "IN", epistemic_CC_DT_IN, 1),
              ("PRP" , epistemic_PRP, 1),
              ("PRP$", epistemic_PRP, 1),
              ( "WP" , epistemic_PRP, 1)):
                # "likely" => weight 1, "very likely" => weight 2
                if i > 0 and s(S[i-1]) in MODIFIERS:
                    weight += 1
                # likely" => score 0.25 (neutral inclining towards positive).
                if w.type and w.type.startswith(type):
                    for k, v in dict.items():
                        # Prefer lemmata.
                        if (w.lemma or s(w)) in v: 
                            # Reverse score for negated terms.
                            if i > 0 and s(S[i-1]) in ("not", "n't", "never", "without"):
                                k = -k * 0.5
                            n += weight * k
                            m += weight
                            break
            # Numbers, citations, explanations make the sentence more factual.
            if w.type in ("CD", "\"", "'", ":", "("):
                n += 0.75
                m += 1
    if m == 0:
        return 1.0 # No modal verbs/adverbs used, so statement must be true.
    return max(-1.0, min(n / (m or 1), +1.0))

def uncertain(sentence, threshold=0.5):
    return modality(sentence) <= threshold