Spaces:
Running
Running
| """Lexical features from the interviewee's words (computable from any transcript).""" | |
| import re | |
| import numpy as np | |
| FILLERS = re.compile(r"\b(um+|uh+|uhm+|er+|ah+|hmm+|like|you know|i mean|kind of|sort of|basically|actually)\b") | |
| POS = set("good great love enjoy excited happy interesting passion passionate fun amazing excellent best success successful proud glad".split()) | |
| NEG = set("bad hard difficult problem problems stress stressed worried hate fail failed failure wrong sorry unfortunately".split()) | |
| TENTATIVE = set("maybe perhaps guess probably possibly somewhat seems".split()) | |
| WE = {"we", "us", "our", "team", "together"} | |
| I = {"i", "me", "my", "i'm", "i've", "myself"} | |
| def interviewee_turns(transcript: str): | |
| turns = [] | |
| for t in transcript.split("|"): | |
| if ":" in t: | |
| who, text = t.split(":", 1) | |
| if who.strip().lower().startswith("interviewee"): | |
| turns.append(re.sub(r"\[.*?\]", " ", text).strip()) | |
| return [t for t in turns if t] | |
| def text_features(turns): | |
| text = " ".join(turns).lower() | |
| words = re.findall(r"[a-z']+", text) | |
| n = max(len(words), 1) | |
| sents = [s for s in re.split(r"[.!?]+", text) if s.strip()] | |
| uniq = len(set(words)) | |
| return { | |
| "txt_words": len(words), | |
| "txt_words_per_turn": len(words) / max(len(turns), 1), | |
| "txt_type_token": uniq / n, | |
| "txt_unique_words": uniq, | |
| "txt_filler_rate": len(FILLERS.findall(text)) / n, | |
| "txt_i_rate": sum(w in I for w in words) / n, | |
| "txt_we_rate": sum(w in WE for w in words) / n, | |
| "txt_pos_rate": sum(w in POS for w in words) / n, | |
| "txt_neg_rate": sum(w in NEG for w in words) / n, | |
| "txt_tentative_rate": sum(w in TENTATIVE for w in words) / n, | |
| "txt_number_rate": len(re.findall(r"\b\d+\b|\b(one|two|three|four|five|ten|hundred|percent)\b", text)) / n, | |
| "txt_avg_word_len": float(np.mean([len(w) for w in words])) if words else 0, | |
| "txt_avg_sentence_len": len(words) / max(len(sents), 1), | |
| "txt_long_word_rate": sum(len(w) >= 7 for w in words) / n, | |
| "txt_because_rate": len(re.findall(r"\b(because|so that|therefore|which meant|as a result)\b", text)) / n, | |
| } | |