File size: 11,355 Bytes
40fc86d 4fde834 40fc86d 4fde834 40fc86d 4fde834 40fc86d 4fde834 40fc86d 4fde834 40fc86d 4fde834 40fc86d 4fde834 40fc86d 4fde834 40fc86d 4fde834 40fc86d 4fde834 40fc86d 4fde834 40fc86d 4fde834 40fc86d 4fde834 40fc86d 4fde834 40fc86d 4fde834 40fc86d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 | import math
import re
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity
from sentence_transformers import SentenceTransformer
class CohesionModule:
def __init__(self):
self.model = SentenceTransformer('all-MiniLM-L6-v2')
self.conn_map_en = {
"AdPos": ["also", "moreover", "furthermore", "in addition", "plus",
"equally", "likewise", "similarly", "as well", "alike",
"additionally", "what's more", "not only", "coupled with",
"along with", "including", "together with", "in conjunction with",
"along the same lines", "correspondingly"],
"AdNeg": ["instead", "conversely", "rather", "on the contrary",
"alternatively", "nonetheless", "however", "nevertheless",
"by contrast", "on the other hand", "in contrast", "unlike",
"despite this", "notwithstanding", "even so", "still",
"be that as it may", "in spite of", "rather", "whereas"],
"CausPos": ["therefore", "hence", "thus", "consequently", "accordingly",
"so", "as a result", "because of this", "for this reason",
"since", "given that", "inasmuch as", "seeing that", "seeing as",
"in view of", "in light of", "due to", "owing to", "stemming from", "insofar as"],
"CausNeg": ["nevertheless", "however", "despite", "in spite of",
"notwithstanding", "still", "yet", "albeit",
"even though", "although", "whereas", "while",
"in contrast", "on the other hand", "conversely",
"be that as it may", "nonetheless", "regardless",
"irrespective of", "granted that"],
"TempPos": ["then", "subsequently", "afterwards", "later", "next",
"thereafter", "following this", "after that", "meanwhile",
"subsequently", "instantly", "immediately", "directly",
"thereupon", "forthwith", "straightaway", "presently",
"quickly", "in due course", "momentarily"],
"TempNeg": ["previously", "beforehand", "earlier", "prior",
"until", "before", "ahead of time",
"in advance", "beforehand", "previously", "heretofore",
"ere", "antecedently", "in anticipation", "preparatory",
"in preparation", "in readiness", "in prospect", "preemptively"],
"LogPos": ["indeed", "actually", "in fact", "clearly",
"evidently", "obviously", "certainly", "surely",
"undoubtedly", "unquestionably", "without doubt",
"assuredly", "definitely", "absolutely", "positively",
"categorically", "decidedly", "indubitably", "unmistakably", "truly"],
"LogNeg": ["conversely", "on the contrary", "inversely",
"contrariwise", "alternatively", "rather",
"by contrast", "in contrast", "on the other hand",
"oppositely", "counter to", "in opposition",
"the other way around", "in a different light",
"from another perspective", "viewed differently",
"seen from another angle", "to the contrary",
"in another sense", "constructively"]
}
self.conn_map_it = {
"AdPos": ["inoltre", "in aggiunta", "ugualmente", "analogamente", "allo stesso modo",
"parimenti", "similmente", "per di più", "oltretutto", "altresì",
"anche", "pure", "persino", "perfino", "nonché",
"oltre a ciò", "a questo si aggiunge", "non solo", "insieme a",
"in più", "tanto quanto", "al pari di", "così come", "d'altronde"],
"AdNeg": ["invece", "al contrario", "per contro", "d'altro canto", "viceversa",
"tuttavia", "però", "eppure", "nondimeno", "ciononostante",
"nonostante ciò", "al tempo stesso", "in contrasto", "a differenza di",
"diversamente", "contrariamente", "piuttosto", "in realtà", "anzi",
"bensì", "ma", "senonché", "fatta eccezione per", "a meno che"],
"CausPos": ["quindi", "pertanto", "di conseguenza", "dunque", "perciò",
"per questo motivo", "per tale ragione", "così", "ecco perché",
"ne consegue che", "da ciò deriva", "in virtù di ciò", "a seguito di",
"per effetto di", "grazie a", "poiché", "dato che", "siccome",
"visto che", "dal momento che"],
"CausNeg": ["nonostante", "sebbene", "benché", "malgrado", "pur",
"anche se", "quantunque", "per quanto", "a dispetto di",
"in barba a", "con tutto che", "pur tuttavia", "nel caso in cui",
"fermo restando che", "ciononostante", "neppure così", "eppure",
"tuttavia", "nondimeno", "ugualmente"],
"TempPos": ["poi", "successivamente", "in seguito", "dopo", "dopodiché",
"in seguito a", "più tardi", "nel frattempo", "subito dopo",
"immediatamente", "a breve", "poco dopo", "contemporaneamente",
"nel contempo", "alla fine", "infine", "per ultimo", "da quel momento",
"a partire da allora", "in quello stesso istante"],
"TempNeg": ["prima", "precedentemente", "in anticipo", "in precedenza", "già",
"tempo prima", "in passato", "fino a quel momento", "sino ad allora",
"antecedentemente", "prima ancora", "fin dall'inizio", "ab initio",
"precocemente", "fin da subito", "in anticipo su", "prima di",
"anteriormente", "per l'appunto prima", "al momento precedente"],
"LogPos": ["infatti", "in effetti", "certamente", "ovviamente", "naturalmente",
"di certo", "senza dubbio", "evidentemente", "chiaramente",
"indubbiamente", "innegabilmente", "senz'altro", "con certezza",
"in verità", "invero", "difatti", "com'è noto", "come si sa",
"come è ovvio", "è indubbio che"],
"LogNeg": ["al contrario", "per contro", "inversamente", "d'altra parte",
"in senso opposto", "in modo inverso", "ribaltando il ragionamento",
"al posto di", "piuttosto che", "contrariamente a quanto detto",
"in modo contrario", "a rovescio", "viceversa", "nel senso opposto",
"cambiando prospettiva", "vista da un altro angolo",
"in tutt'altro senso", "in senso contrario", "anziché", "in alternativa"]
}
def _get_jaccard(self, sets):
"""Calcola l'indice di Jaccard per una lista di N set."""
if not all(sets):
return 0.0
intersection = set.intersection(*sets)
union = set.union(*sets)
return len(intersection) / len(union) if len(union) > 0 else 0.0
def analyze(self, doc, sentences, tokens_text, token_text_SP, lang="en"):
# Seleziona il dizionario connettivi in base alla lingua
self.conn_map = self.conn_map_it if lang == "it" else self.conn_map_en
# 1. RAGGRUPPAMENTO IN PARAGRAFI
paragraphs = []
current_para = []
for sent in sentences:
current_para.append(sent)
if "\n" in sent.text_with_ws:
paragraphs.append(current_para)
current_para = []
if current_para:
paragraphs.append(current_para)
# 2. ACCUMULATORI
lex_scores_2, lex_scores_3 = [], []
sem_scores_sent, sem_scores_para = [], []
para_embeddings = []
# 3. ANALISI PER PARAGRAFO
for paragraph in paragraphs:
if len(paragraph) < 2:
para_embeddings.append(self.model.encode(paragraph[0].text))
continue
target_pos = {"NOUN", "VERB", "ADJ", "PROPN"}
sent_lemmas = [
{t.lemma_.lower() for t in s if t.pos_ in target_pos and not t.is_punct}
for s in paragraph
]
# --- Analisi Lessicale ---
for i in range(len(sent_lemmas) - 1):
lex_scores_2.append(self._get_jaccard([sent_lemmas[i], sent_lemmas[i + 1]]))
if len(sent_lemmas) >= 3:
for i in range(len(sent_lemmas) - 2):
lex_scores_3.append(self._get_jaccard([sent_lemmas[i], sent_lemmas[i + 1], sent_lemmas[i + 2]]))
# --- Analisi Semantica (Livello Frase) ---
texts = [s.text for s in paragraph]
sent_embs = self.model.encode(texts)
for i in range(len(sent_embs) - 1):
sim = cosine_similarity(sent_embs[i].reshape(1, -1), sent_embs[i + 1].reshape(1, -1))[0][0]
sem_scores_sent.append(float(sim))
para_full_text = " ".join(texts)
para_embeddings.append(self.model.encode(para_full_text))
# --- 4. ANALISI SEMANTICA (Livello Paragrafo) ---
if len(para_embeddings) > 1:
for i in range(len(para_embeddings) - 1):
sim = cosine_similarity(para_embeddings[i].reshape(1, -1), para_embeddings[i + 1].reshape(1, -1))[0][0]
sem_scores_para.append(float(sim))
full_text_lower = doc.text.lower()
conns = {}
for cat, words in self.conn_map.items():
count = 0
for phrase in words:
pattern = rf"\b{re.escape(phrase.lower())}\b"
count += len(re.findall(pattern, full_text_lower))
conns[cat] = count
wsum = (
(conns.get("AdPos", 0) + conns.get("AdNeg", 0) * 1.5) +
(conns.get("CausPos", 0) + conns.get("CausNeg", 0) * 2) +
(conns.get("TempPos", 0) + conns.get("TempNeg", 0)) +
(conns.get("LogPos", 0) + conns.get("LogNeg", 0) * 1.5)
)
valori = list(conns.values())
stand_dev = np.std(valori) if valori else 0
generalValue = math.log(stand_dev, wsum) if wsum > 0 and wsum != 1 and stand_dev > 0 else 0.0
return {
"connectors": {k: round((v / len(token_text_SP)) * 1000, 2) for k, v in conns.items()},
"general_cohesion": round(generalValue, 4) if wsum > 0 else 0.0,
"lexical_cohesion_local": np.mean(lex_scores_2) if lex_scores_2 else 0.0,
"lexical_cohesion_global": np.mean(lex_scores_3) if lex_scores_3 else 0.0,
"semantic_cohesion_sentences": np.mean(sem_scores_sent) if sem_scores_sent else 0.0,
"semantic_cohesion_paragraphs": np.mean(sem_scores_para) if sem_scores_para else 0.0,
"stats": {
"num_paragraphs": len(paragraphs),
"num_sentences": len(sentences)
}
}
|