Table 4.
Forecasting results.
| Climate overall | Personal climate | Economic climate | Current climate | Future climate | |
|---|---|---|---|---|---|
| AR(2) | 1.000*** | 1.000*** | 1.000*** | 1.000*** | 1.000** |
| AR(2) + sentiment | 0.434* | 0.484** | 0.455 | 0.471* | 0.426 |
| AR(2) + SBS ERK | 0.391 | 0.394 | 0.396 | 0.429 | 0.432 |
| AR(2) + SBS ERK + sentiment | 0.432* | 0.489** | 0.415 | 0.439 | 0.418 |
| AR(2) + prevalence | 0.410** | 0.394 | 0.407 | 0.421 | 0.432 |
| AR(2) + diversity | 0.422 | 0.394 | 0.402 | 0.403 | 0.463 |
| AR(2) + connectivity | 0.394 | 0.394 | 0.396 | 0.403 | 0.432 |
| BERT truncated | 1.076*** | 1.107*** | 0.992** | 1.134*** | 1.089** |
| BERT chunk | 1.104*** | 1.131*** | 1.060** | 1.100*** | 1.141** |
Bold figures indicate the best forecasting models. Italic figures are those for which the Diebold-Mariano test rejects the null hypothesis of equal predictive accuracy with respect to the best forecasting model at a significance level of 0.1 (*), 0.05 (**), or 0.01 (***).