Skip to main content

Table 2 Evaluation results over the REN-10k dataset

From: Readers’ affect: predicting and understanding readers’ emotions with deep learning

Model

Acc@1 (%)\(\uparrow\)

\(\hbox {AP}_{{\mathrm{document}}}\uparrow\)

\(\hbox {AP}_{{\mathrm{emotion}}}\uparrow\)

\(\hbox {RMSE}_{\mathrm{D}}\downarrow\)

\(\hbox {WD}_{\mathrm{D}}\downarrow\)

Bi-LSTM + Attention (Our Method)

60.55

0.7994

0.5596

0.1500

0.0812

Deep learning baselines

 sent2affect [48]

49.39

0.5716

0.1004

0.2383

0.1298

 SS-BED [44]

55.11

0.7090

0.4944

0.2209

0.1202

 Kim’s CNN [64]

49.03

0.5893

0.1610

0.2332

0.1322

 Bi-LSTM [48]

52.80

0.6282

0.4804

0.2215

0.1202

 LSTM [9]

52.07

0.6064

0.4581

0.2223

0.1204

 GRU

50.17

0.6012

0.2013

0.2329

0.1293

Lexicon based baselines

 SWAT [11]

51.28

0.6151

0.3483

0.2551

0.1472

 Emotion Term Model [12]

53.57

0.6023

0.0115

0.3343

0.2520

 Synesketch [33]

35.86

0.1632

0.2326

0.2677

0.1664

Problem transformation baselines

 WMD [39]

43.56

0.2366

0.0981

0.3156

0.1480

 TF-IDF [39, 48]

49.47

0.6019

0.3133

0.2347

0.1235

 N-Grams [32, 44] (\(N=1\))

48.85

0.5331

0.2512

0.2362

0.1251

 TEC [32]

50.90

0.6035

0.3133

0.2460

0.1297

 TEI [32]

50.90

0.6088

0.3147

0.2301

0.1243

 MEI [32]

50.85

0.6029

0.2379

0.2310

0.1255

 GEC [32] (\(\delta = 0.25\))

50.67

0.6021

0.2765

0.2388

0.1238

 GEI [32] (\(\delta = 0.25\))

50.63

0.6007

0.2731

0.2392

0.1232

 Sentiment word count [32, 65]

50.12

0.6050

0.1939

0.2323

0.1274

 SSWEu [63] (\(d=50\))

49.48

0.5726

0.0714

0.2384

0.1280

 GloVe [44] (\(d=100\))

49.63

0.5670

0.0716

0.2390

0.1279

Algorithm adaptation baselines

 TF-IDF [39, 48]

50.17

0.6071

0.2555

0.2303

0.1268

 N-Grams [32, 44] (\(N=1\))

50.03

0.5829

0.2173

0.2354

0.1347

 TEC [32]

50.51

0.6625

0.3523

0.2257

0.1214

 TEI [32]

53.80

0.6516

0.3211

0.2252

0.1209

 MEI [32]

49.53

0.5713

0.1859

0.2380

0.1291

 GEC [32] (\(\delta = 0.25\))

51.24

0.6423

0.2758

0.2285

0.1218

 GEI [32] (\(\delta = 0.25\))

52.60

0.6163

0.2322

0.2221

0.1269

 Sentiment word count [32, 65]

50.36

0.6014

0.1839

0.2331

0.1254

 SSWEu [63] (\(d=50\))

49.44

0.5173

0.0984

0.3751

0.1330

 GloVe [44] (\(d=100\))

49.44

0.5169

0.0509

0.3758

0.1334

  1. The best results within each category have been shown in boldface