Table 3 Evaluation results over the RENh-4k dataset

Bi-LSTM + Attention (Our Method)

50.50

0.6499

0.4054

0.2301

0.1220

Deep learning baselines

 sent2affect [48]

36.00

0.4684

0.1047

0.2508

0.1458

 SS-BED [44]

45.62

0.5534

0.3609

0.2406

0.1424

 Kim’s CNN [64]

40.00

0.4775

0.2084

0.2493

0.1585

 Bi-LSTM [48]

45.00

0.6297

0.3415

0.2400

0.1465

 LSTM [9]

40.13

0.5927

0.3402

0.2559

0.1472

 GRU

38.75

0.4860

0.1765

0.2481

0.1443

Lexicon based baselines

 SWAT [11]

43.75

0.5858

0.3005

0.2561

0.1608

 Emotion Term Model [12]

44.10

0.5520

0.0102

0.3369

0.2000

 Synesketch [33]

31.37

0.1394

0.2423

0.2936

0.1792

Problem transformation baselines

 WMD [39]

35.25

0.3593

0.0289

0.2869

0.1346

 TF-IDF [39, 48]

44.37

0.5007

0.3490

0.2440

0.1316

 N-Grams [32, 44] \((N=1)\)

42.37

0.5067

0.3009

0.2662

0.1328

 TEC [32]

41.12

0.5686

0.3237

0.2410

0.1357

 TEI [32]

44.06

0.5908

0.3532

0.2409

0.1316

 MEI [32]

40.75

0.5394

0.2574

0.2442

0.1411

 GEC [32] (\(\delta =0.25\))

42.75

0.5676

0.3063

0.2410

0.1363

 GEI [32] (\(\delta =0.25\))

41.75

0.5602

0.2963

0.2417

0.1365

 Sentiment word count [32, 65]

39.25

0.4883

0.1443

0.2492

0.1386

 SSWE_u [63] (\(d=50\))

41.50

0.4969

0.1804

0.2483

0.1367

 GloVe [44] (\(d=100\))

40.75

0.5108

0.2072

0.2474

0.1327

Algorithm adaptation baselines

 TF-IDF [39, 48]

39.62

0.4630

0.2870

0.2516

0.1489

 N-Grams [32, 44] (\(N=1\))

42.75

0.4926

0.2796

0.2456

0.1505

 TEC [32]

41.37

0.5701

0.3298

0.2496

0.1356

 TEI [32]

42.87

0.6029

0.3528

0.2473

0.1343

 MEI [32]

40.12

0.4856

0.2279

0.2488

0.1466

 GEC [32] (\(\delta = 0.25\))

44.75

0.5726

0.3190

0.2406

0.1359

 GEI [32] (\(\delta = 0.25\))

41.37

0.5532

0.2934

0.2419

0.1378

 Sentiment word count [32, 65]

39.62

0.4846

0.1343

0.2491

0.1425

 \(\hbox {SSWE}_{\mathrm{u}}\) [63] (\(d=50\))

35.62

0.3080

0.0207

0.4246

0.1376

 GloVe [44] (\(d=100\))

35.37

0.2382

0.0920

0.4373

0.1376