Emoticons, or text-based representation of a face, emerged relatively early as a means of signaling that a message posted on a message board was to be taken seriously (or not). Emoji (as used in digital communication) are a more recent development and are actually pictographs (i.e., a pictorial sign or symbol as with: Fig A in S1 File). Hence, what an emoji can look like is not limited to the characters on a keyboard, but instead can depict a myriad of different facial expressions with varying levels of detail (e.g., sweat rolling down one’s face, reddened cheeks, bulging eyes). Additionally, because of their pictorial nature, emoji are not just limited to faces; emoji exist resembling an array of different objects (e.g., national flags, vehicles, various foods), animals, hand gestures (e.g., thumbs up, praying), and behaviors (e.g., dancing, running).

One popular view of emoticons is that they are used primarily to convey affective meaning [5,6,7,8,9]. Consistent with this, emoticons have been found to influence the perceived valence of text messages. For example, Derks, Bos, and von Grumbkow [5] found that participants rated messages that included emoticons as more intense than the same messages without emoticons. Other research suggests that when the valence of an emoticon is incongruent with the valence of the text, the message will be interpreted as ambiguous [10] and this can sometimes result in the sender’s message being perceived as sarcastic [8]. Kavenagh [11] examined the possibility that emoticons might sometimes be used as politeness markers. In a study of Japanese and U.S. bloggers, he found that emoticons were used by bloggers from both countries (though significantly more by the former than the latter), and could function as both a positive politeness (enhance closeness) and negative politeness (lessen imposition) marker [12].

Other scholars have argued that emoticons are not just affective, but also can serve a more pragmatic function and act as illocutionary force indicating devices thereby helping to disambiguate the sender’s intention [13]. Some research supports this idea. For example, Thompson and Filik [14] asked participants to attempt to make their intentions clear in a texting situation, either by making changes to a text message (Experiment 1) or creating their own message. Of interest was the use of emoticons. In both experiments, participants were significantly more likely to use emoticons when the intent was sarcastic rather than literal.

In a related study, Filik and Thompson [15] examined perceptions of literal and sarcastic messages as a function of whether the message included emoticons, various types of punctuation, or neither. The interpretation of an intended sarcastic message was not impacted by emoticons or punctuation when there was contextual support and the meaning clear. However, intended literal messages were more likely to be perceived as sarcastic when the message included emoticons. In contrast, when the intended meaning was ambiguous, including an emoticon (wink emoticon) increased the likelihood of sarcastic intent being recognized. Research conducted by Riordan [16, 17] suggests that these effects are not limited to face emoji. In several studies she demonstrated that the inclusion of nonface emoji in a message can reduce perceived ambiguity, and increase interpretation confidence, in addition to influencing judgments of conveyed affect, especially positive affect.

More recently, Weissman and Tanner [18] demonstrated that emojis (wink) used to convey irony generally elicit the same neural responses as irony conveyed with words. Specifically, they observed enhanced P200s (an early indicator of attention-related processes) and P600s (reflecting reanalysis or integration processes) to wink emoji. Importantly, judgments of irony correlated with the occurrence of a P600; i.e., participants who interpreted the message as ironic were more likely to display a P600. There does appear to be a processing cost associated with emoji, at least in some situations. Cohen et al. [19] examined comprehension processes when emoji were substituted for words. They examined both nouns (e.g., Fig A in S1 File for pizza) and verbs (e.g., Fig B in S1 File for love). They found a processing cost for the use of emoji (for both nouns and verbs) as indexed with self-paced reading times, a finding consistent with the enhanced P600 reported by Weissman and Tanner [18]. Interestingly, they found no differences between words and their emoji substitutes in terms of their comprehensibility.

If emoji are communicative and (sometimes) designed to disambiguate a speaker’s intended meaning, it seems that this would be most likely to occur when the intended meaning is ambiguous or indirect. There are multiple types of indirect meaning, although research has focused primarily on metaphor, sarcasm, and irony. In prior research [20, 21] we investigated the comprehension of potentially face-threatening indirect replies, a more ambiguous type of indirect meaning. Indirect replies are responses to questions in which the speaker does not provide a direct answer, and in so doing violates the Gricean [22] maxim of relation (make your contribution relevant to the exchange). For example, when Mark replies “It’s hard to give a good presentation” in response to Nick’s question “What did you think of my presentation?” observers typically reason that Mark thought poorly of Nick’s presentation and is conveying that negative opinion indirectly. Research suggests that the generation of this implicature is relatively time-consuming, and involves the activation and subsequent rejection of the literal meaning of the reply [20,21]. In Gricean terms this would be considered a particularized implicature; i.e., the interpretation of the intended meaning is entirely context dependent. Recent research suggests that comprehension of this type of indirect reply involves recruitment of brain areas involved in empathy (Right Anterior Cingulate Cortex) and inferencing (Right Superior Temporal Gyrus) [23].

As particularized implicatures, the interpretation of indirect replies requires attention to contextual cues that provide support for the intended indirect meaning. Linguistic cues can serve this function and one important class of terms in this regard is dispreferred markers. Dispreferred turn markers can take the form of delays and hesitations (‘hehh’, silent pauses), space takers (‘well’, ‘you know’), or more specific forms, like token agreements before contradiction (‘yes, but… ‘). These markers typically occur at the beginning of a turn and indicate that the present contribution is the opposite of what would be ideally expected in a cooperative interaction, that is, the turn is dispreferred in some sense; e.g., disagreeing, rejecting, blaming [24,25,26].

Research suggests that dispreferred markers can influence the interpretation of scalar expressions (e.g., some, sometimes, etc.), words that are ambiguous and interpreted differently as a function of the context [27]. More importantly, our prior research demonstrated how the discourse marker “well” can influence the comprehension of indirect replies [28]. Participants in these studies read brief question–indirect reply sequences and then indicated how the reply should be interpreted. On critical trials the interpretation following the reply was an indirect, face-threatening interpretation and the speed with which this interpretation was endorsed served as the primary dependent measure. Verification of the indirect meaning was significantly faster on the “well” trials relative to the trials in which the reply did not contain the “well” preface. Hence, the presence of the dispreferred marker “well” facilitated recognition of the speaker’s intended indirect meaning.

The purpose of the present research was to examine the role played by emoji in the processing of potentially face-threatening indirect replies. To do this, we modified the procedure used by Holtgraves [28] and substituted emoji for the dispreferred marker “well”. Participants read situation descriptions followed by a question and reply to that question. The reply either contained an emoji or did not, and the emoji was presented either at the beginning of the reply (Experiment 1) or at the end of the reply (Experiment 2). After reading the reply, participants were asked to indicate their judgment (Yes or No) of whether the paraphrase was a reasonable interpretation of the preceding reply; on critical trials the paraphrase was a face-threatening indirect interpretation. Participants endorsement of that interpretation, and the speed with which they endorsed it, served as dependent measures. We reasoned that emoji could function similarly to dispreferred markers and facilitate recognition of the intended indirect meaning. Hence, we expected participants to be more likely to endorse the indirect interpretation, and to do so more quickly, when the reply contained an emoji than when it did not contain an emoji. In addition, we examined the possibility that a reply consisting of an emoji only (i.e., with no corresponding text) might function just like a reply containing text and an emoji, as well as whether it made any difference if the emoji occurred at the beginning of the reply (Experiment 1) or at the end of the reply (Experiment 2).

The purpose of this experiment was to examine the impact of emoji on the endorsement of indirect interpretations. Participants read scenarios, questions, and indirect replies and then judged the meaning of the reply. We expected emoji to facilitate recognition of the indirect meaning (increased accuracy and decreased response time) of a reply, relative to the same reply without an emoji.

The purpose of this experiment was to replicate Experiment 1 and to examine the possible effect of emoji location. Rather than placing the emoji before the text as in Experiment 1, in this experiment the emoji was placed after the text (for the text plus emoji condition).

Speakers often convey their intended meanings indirectly. Metaphors, hints, indirect requests, and so on are all examples of indirect meaning. In these instances, aspects of the context become critical for recognizing what the speaker intends to convey. Sarcasm, for example, is often recognized via the speaker’s tone of voice. In fact, sarcasm comprehension often depends less on “what” was said and more on “how” it was said [30,31]. The wealth of contextual features that are available in face-to-face communication are, of course, absent in the digital realm, and substitutes, including emoji, have emerged to aid in the communicative process.

Prior research on the communicative functions of emoji is limited. However, there has been some research demonstrating that emoji (and emoticons) can play a role in the recognition of sarcasm and irony [8,14]. In the present research we explored the role of emoji in the interpretation of potentially face-threatening, indirect replies. Indirect replies of the type examined here are ambiguous on the surface, their literal meaning violates the relevance maxim. Although such meanings appear to be routinely recognized [21], the present studies demonstrate that (some) emoji can facilitate this comprehension process. Specifically, we found that these intended, indirect meanings are recognized more often, and more quickly, when the reply contained an emoji (either alone or with text). This facilitation occurred even when there was no text, that is, an emoji alone was sufficient. Moreover, when the reply contained text and an emoji, it made no difference if the emoji was presented before or after the text, interpretation was still facilitated.

Even though comprehension was facilitated with replies containing only an emoji, as well as with replies containing both text and emoji, it is possible that the comprehension processes will be different in these two situations. In the latter situation, emoji likely function as part of the context and serve to guide the recipient to the recognition of the indirect meaning, much like facial expressions do in face-to-face interaction [1]. In contrast, when an emoji occurred without any text, the emoji itself was the reply and hence there were no words to disambiguate. This is not to say that emoji, at least those used in the current research, contain semantic content. Rather, their occurrence, combined with the lack of any words in response to the preceding question, likely prompts the recipient to infer a face-threatening meaning. Without any words in the reply, recipients must work out the intended meaning on their own, without any textual support. What this suggests, then, is that the processing of emoji may turn out to pattern like other language variables; multiple processes are likely involved in their comprehension.

Although emoji facilitated the comprehension of indirect replies for disclosures and opinions, it did not facilitate recognition of the intended meaning of request refusals. One likely reason for this difference is the role of conventionality. Indirect meanings can be conveyed in various ways, and one important dimension in this regard is conventionality. The types of indirect replies in this research were all excuses, that is, they functioned by asserting a reason for why the information was negative (for opinions and disclosures) or for why the speaker would not comply with the request (for the request refusals). There is, however, a difference between the requests for information (opinions and disclosures) and requests for action. For the latter, there is a close connection between the underlying preconditions that can be used for both performing the request indirectly and refusing the request indirectly [32]. For example, a speaker can question the hearer’s ability to perform the requested action (e.g., Can you shut the window?). These same preconditions can be denied as a means of (indirectly) refusing to comply with the request (e.g., I can’t reach it). Thus, by denying a precondition for the performance of a request, one can conventionally refuse to comply with the request. In contrast, for opinions and disclosures, there are no preconditions that could be asserted in order to convey a negative opinion or disclosure. One could refuse to provide the requested information by indicating a lack of willingness (e.g., I don’t want to tell you). But it’s not possible to convey a negative opinion or disclosure in this way. Consistent with this difference, Holtgraves [21] found that excuses serving as replies to opinions and disclosures required an inference process (recognize and reject the literal meaning) for comprehension, but excuses serving as replies to requests did not (i.e., they were recognized directly). The present results are consistent with this finding. Indirect replies that require an inference process for comprehension (replies to opinions and disclosures) are nonconventional, and hence available contextual cues can facilitate recognition of the intended meaning. These same contextual cues will have little effect in the comprehension of replies that are conventional (request refusals in this case) and hence recognized directly. Note that this pattern is similar to that reported by Filik and Thompson [15] who found that emoticons increased the likelihood of perceived sarcastic intent when the intended meaning was ambiguous, and not when there was clear contextual support for the sarcastic meaning.

Although in this research emoji facilitated recognition of intended indirect meaning for opinions and disclosures, there is no guarantee that emoji will always be facilitative. This is because the meaning of emoji is often ambiguous. For example, Miller et al [29] found that when participants rated the same emoji rendering, they disagreed on whether the conveyed sentiment was positive, neutral, or negative 25% of the time. Because of this it seems likely that emoji will sometimes hinder recognition of a sender’s intended meaning. Still, emoji are ubiquitous, and users likely believe their use facilitates communication. It may be that the successful communicative use of emoji is unique to communicative dyads. That is, over time individuals in digital contact with one another may come to use and understand the meaning of certain (perhaps idiosyncratic) emoji. Future research should be directed toward examining when emoji can hinder rather than facilitate the recognition of communicative intent.