Testing the limits of contextual constraint: Interactions with word frequency and parafoveal preview during fluent reading

Abstract

Contextual constraint is a key factor affecting a word's fixation duration and its likelihood of being fixated during reading. Previous research has generally demonstrated additive effects of predictability and frequency in fixation times. Studies examining the role of parafoveal preview have shown that greater preview benefit is obtained from more predictable and higher frequency words versus less predictable and lower frequency words. In two experiments, we investigated effects of target word predictability, frequency and parafoveal preview. A 3 (Predictability: low, medium, high) × 2 (Frequency: low, high) design was used with Preview (valid, invalid) manipulated between experiments. With valid previews, we found main effects of Predictability and Frequency in both fixation time and fixation probability measures, including an interaction in early fixation measures. With invalid preview, we again found main effects of Predictability and Frequency in fixation times, but no evidence of an interaction. Fixation probability showed a weak Predictability effect and Predictability-Frequency interaction. Predictability interacted with Preview in early fixation time and fixation probability measures. Our findings suggest that high levels of contextual constraint exert an early influence during lexical processing in reading. Results are discussed in terms of models of language processing and eye movement control.

Keywords: Contextual predictability; eye movements; parafoveal preview; reading; word frequency.

Figure 1.

Single fixation duration (ms) on target words (with standard error bars) as a function of Predictability (LP, MP, HP), Frequency (LF, HF) and Preview (Valid, Invalid). LF, low frequency; HF, high frequency; LP, low predictability; MP, medium predictability; HP, high predictability.