Create services/absa.py

services/absa.py

@@ -0,0 +1,275 @@
+"""
+services/absa.py
+Aspect-Based Sentiment Analysis (ABSA) untuk Bahasa Indonesia.
+
+Pendekatan:
+1. Ekstrak aspek dari teks menggunakan lexicon + dependency pattern
+2. Tentukan sentimen per aspek menggunakan window context
+3. Agregasi hasil per kategori aspek
+
+Kategori aspek yang didukung (domain-agnostic):
+  - harga/biaya       : harga, mahal, murah, biaya, tarif, ongkos
+  - kualitas/produk   : kualitas, bagus, jelek, rusak, bagus, produk
+  - pelayanan/service : pelayanan, layanan, respon, lambat, cepat, ramah
+  - lokasi/tempat     : lokasi, tempat, jarak, strategis, jauh, dekat
+  - kebijakan         : kebijakan, aturan, regulasi, keputusan, program
+  - pemimpin/tokoh    : pemimpin, presiden, gubernur, menteri, pejabat
+  - ekonomi           : ekonomi, inflasi, harga, pendapatan, gaji, subsidi
+  - pendidikan        : pendidikan, sekolah, kampus, belajar, kurikulum
+  - kesehatan         : kesehatan, rumah sakit, dokter, obat, vaksin
+  - infrastruktur     : jalan, infrastruktur, gedung, fasilitas, listrik
+"""
+
+import re
+from collections import defaultdict
+from typing import Optional
+
+# ─────────────────────────────────────────────
+# ASPECT LEXICON
+# ─────────────────────────────────────────────
+ASPECT_LEXICON = {
+    'harga': [
+        'harga','mahal','murah','biaya','tarif','ongkos','harganya',
+        'cost','price','bayar','bayaran','budget','anggaran','tagihan',
+        'cicilan','kredit','diskon','promo','gratis','terjangkau'
+    ],
+    'kualitas': [
+        'kualitas','bagus','jelek','buruk','rusak','cacat','produk',
+        'barang','mutu','kualiti','quality','performa','fitur','spesifikasi',
+        'durable','tahan lama','awet','rapuh','boros'
+    ],
+    'pelayanan': [
+        'pelayanan','layanan','servis','service','respon','respons','lambat',
+        'cepat','ramah','kasar','profesional','sopan','membantu','helpful',
+        'cs','customer service','admin','operator','staff','petugas'
+    ],
+    'lokasi': [
+        'lokasi','tempat','jarak','strategis','jauh','dekat','akses',
+        'parkir','alamat','wilayah','daerah','kawasan','lingkungan'
+    ],
+    'kebijakan': [
+        'kebijakan','aturan','regulasi','keputusan','program','peraturan',
+        'undang','hukum','sanksi','denda','izin','prosedur','birokrasi',
+        'pemerintah','pemerintahan','politik','implementasi'
+    ],
+    'pemimpin': [
+        'pemimpin','presiden','gubernur','menteri','pejabat','bupati',
+        'walikota','anggota','dewan','partai','calon','kandidat','tokoh',
+        'figur','kepala','direktur','ceo','pimpinan'
+    ],
+    'ekonomi': [
+        'ekonomi','inflasi','deflasi','pendapatan','gaji','upah','subsidi',
+        'pajak','ekspor','impor','investasi','pertumbuhan','resesi','utang',
+        'pinjaman','modal','bisnis','usaha','umkm'
+    ],
+    'pendidikan': [
+        'pendidikan','sekolah','kampus','belajar','kurikulum','guru','dosen',
+        'mahasiswa','siswa','nilai','ujian','beasiswa','biaya sekolah',
+        'spp','kuliah','universitas','sd','smp','sma'
+    ],
+    'kesehatan': [
+        'kesehatan','rumah sakit','dokter','obat','vaksin','rs','puskesmas',
+        'bpjs','asuransi','rawat','operasi','penyakit','covid','virus',
+        'faskes','apotek','tenaga medis','perawat'
+    ],
+    'infrastruktur': [
+        'jalan','infrastruktur','gedung','fasilitas','listrik','air','banjir',
+        'macet','transportasi','tol','jembatan','bandar udara','pelabuhan',
+        'internet','sinyal','jaringan','konstruksi'
+    ],
+}
+
+# ─────────────────────────────────────────────
+# SENTIMENT LEXICON PER ASPECT
+# ─────────────────────────────────────────────
+SENTIMENT_POS = {
+    'bagus','baik','bagus','mantap','keren','hebat','suka','senang','puas',
+    'meningkat','naik','maju','berkembang','berhasil','sukses','bagus',
+    'terjangkau','murah','gratis','ramah','cepat','tepat','profesional',
+    'strategis','dekat','mudah','lancar','aman','nyaman','bersih',
+    'good','great','nice','excellent','best','amazing','happy','love',
+    'wonderful','perfect','outstanding','satisfied','recommended',
+    'mendukung','setuju','approve','pro','positif','memuji','bangga',
+}
+
+SENTIMENT_NEG = {
+    'buruk','jelek','rusak','parah','kecewa','mahal','lambat','lama',
+    'susah','sulit','ribet','boros','kasar','curang','korup','gagal',
+    'turun','menurun','anjlok','jatuh','krisis','masalah','bermasalah',
+    'berbahaya','bahaya','mengecewakan','tidak puas','kapok',
+    'bad','worst','terrible','awful','poor','horrible','hate','dislike',
+    'expensive','slow','failed','disappointed','useless','waste',
+    'menolak','menentang','against','kontra','negatif','mencela','kritik',
+    'bohong','tipu','menipu','korupsi','tidak setuju',
+}
+
+NEGATION_WORDS = {
+    'tidak','bukan','belum','tak','gak','ga','nggak','ngga','jangan',
+    'no','not','never','dont',"don't",'without','tanpa',
+}
+
+INTENSIFIER_POS = {'sangat','banget','sekali','amat','luar biasa','super','paling','bgt'}
+INTENSIFIER_NEG = {'kurang','agak','sedikit','hampir','nyaris'}
+
+
+def _get_aspect(token: str) -> Optional[str]:
+    """Cari aspek untuk satu token."""
+    token = token.lower()
+    for aspect, keywords in ASPECT_LEXICON.items():
+        if token in keywords or any(kw in token for kw in keywords if len(kw) > 4):
+            return aspect
+    return None
+
+
+def _sentiment_score_window(tokens: list, center_idx: int, window: int = 4) -> float:
+    """
+    Hitung skor sentimen dalam window ±N kata dari posisi aspek.
+    Pertimbangkan negasi dan intensifier.
+    Return: float positif = positif, negatif = negatif, 0 = netral
+    """
+    start = max(0, center_idx - window)
+    end   = min(len(tokens), center_idx + window + 1)
+    window_tokens = tokens[start:end]
+
+    score    = 0.0
+    negated  = False
+    intensify = 1.0
+
+    for i, tok in enumerate(window_tokens):
+        tl = tok.lower()
+        if tl in NEGATION_WORDS:
+            negated = True
+            continue
+        if tl in INTENSIFIER_POS:
+            intensify = 1.5
+            continue
+        if tl in INTENSIFIER_NEG:
+            intensify = 0.6
+            continue
+
+        if tl in SENTIMENT_POS:
+            s = 1.0 * intensify
+            score += -s if negated else s
+            negated = False
+            intensify = 1.0
+        elif tl in SENTIMENT_NEG:
+            s = -1.0 * intensify
+            score += -s if negated else s
+            negated = False
+            intensify = 1.0
+
+    return score
+
+
+def _score_to_label(score: float) -> str:
+    if score > 0.3:   return "Positive"
+    if score < -0.3:  return "Negative"
+    return "Neutral"
+
+
+def extract_aspects(text: str) -> list[dict]:
+    """
+    Ekstrak aspek dan sentimen dari satu teks.
+
+    Return: list of {aspect, sentiment, score, mention, context}
+    """
+    if not text or len(text.strip()) < 5:
+        return []
+
+    # Tokenisasi sederhana
+    clean  = re.sub(r'[^\w\s]', ' ', text.lower())
+    tokens = clean.split()
+
+    results   = []
+    seen_aspects = set()
+
+    for i, token in enumerate(tokens):
+        aspect = _get_aspect(token)
+        if aspect is None:
+            continue
+
+        # Hindari duplikat aspek dalam satu kalimat
+        if aspect in seen_aspects:
+            continue
+        seen_aspects.add(aspect)
+
+        score   = _sentiment_score_window(tokens, i)
+        label   = _score_to_label(score)
+
+        # Context window untuk display
+        start   = max(0, i - 3)
+        end     = min(len(tokens), i + 4)
+        context = ' '.join(tokens[start:end])
+
+        results.append({
+            'aspect':    aspect,
+            'sentiment': label,
+            'score':     round(score, 3),
+            'mention':   token,
+            'context':   context,
+        })
+
+    return results
+
+
+def analyze_absa(texts: list[str]) -> dict:
+    """
+    Jalankan ABSA pada list teks.
+
+    Return:
+    {
+      'per_text': list of per-text results,
+      'aggregate': {aspect: {Positive: N, Negative: N, Neutral: N, dominant: str}},
+      'top_aspects': sorted list of most-mentioned aspects,
+      'aspect_sentiment_map': {aspect: dominant_sentiment}
+    }
+    """
+    per_text  = []
+    aggregate = defaultdict(lambda: {'Positive': 0, 'Negative': 0, 'Neutral': 0, 'total': 0})
+
+    for text in texts[:80]:   # batasi untuk performa
+        aspects = extract_aspects(text)
+        per_text.append({'text': text[:100], 'aspects': aspects})
+        for a in aspects:
+            aggregate[a['aspect']][a['sentiment']] += 1
+            aggregate[a['aspect']]['total']         += 1
+
+    # Kalkulasi dominan per aspek
+    agg_result = {}
+    for aspect, counts in aggregate.items():
+        t = counts['total'] or 1
+        dominant = max(
+            ['Positive', 'Negative', 'Neutral'],
+            key=lambda s: counts[s]
+        )
+        agg_result[aspect] = {
+            'Positive':   counts['Positive'],
+            'Negative':   counts['Negative'],
+            'Neutral':    counts['Neutral'],
+            'total':      counts['total'],
+            'pos_pct':    round(counts['Positive'] / t * 100, 1),
+            'neg_pct':    round(counts['Negative'] / t * 100, 1),
+            'neu_pct':    round(counts['Neutral']  / t * 100, 1),
+            'dominant':   dominant,
+        }
+
+    # Sort by total mentions
+    top_aspects = sorted(
+        agg_result.items(),
+        key=lambda x: x[1]['total'],
+        reverse=True
+    )
+
+    aspect_sentiment_map = {
+        asp: data['dominant']
+        for asp, data in top_aspects
+    }
+
+    return {
+        'per_text':            per_text[:20],   # kirim sample ke frontend
+        'aggregate':           agg_result,
+        'top_aspects':         [{'aspect': a, **d} for a, d in top_aspects[:8]],
+        'aspect_sentiment_map': aspect_sentiment_map,
+        'total_texts_analyzed': len(texts),
+        'aspects_found':       len(agg_result),
+    }