Social anxiety disorder (SAD) is a common and impairing condition [1, 2], characterised by a low natural recovery rate [3] and adolescent-onset [4]. Developing effective early interventions has the potential to offset the long-term consequences associated with the disorder [5]. Unfortunately, whilst outcomes from standard psychological treatment approaches are promising for most common anxiety problems in youth, they are significantly worse for youth with SAD (e.g. Hudson, Rapee [6], Ginsburg, Kendall [7], Crawley, Beidas [8], Lundkvist-Houndoumadi and Thastum [9]). Establishing psychological mechanisms of social anxiety in youth that can be reversed in treatment may be one way to improve outcomes for this population [10].

Two of the processes that are emphasised in leading cognitive behavioural accounts of social anxiety in adults [11–14] are self-focused attention and safety behaviours. For example, in the model of Clark & Wells (1995), it is proposed that when entering a social or performance situation, socially anxious adults turn their attention inward, to close monitoring of themselves and how they think they are coming across. This is unhelpful because it prevents the individual from discovering how others are responding to them. It also increases awareness of internal information, such as physical feelings of anxiety and mental images, which the individual may then take as confirmation of their negative beliefs. Safety behaviours are strategies, many of which are mental operations, that are intended to prevent or minimise feared outcomes from occurring [15]. For example, an individual may avoid answering a question for fear of getting the answer wrong and appearing stupid. It is suggested that safety behaviours are unhelpful for a number of reasons. They prevent the individual from discovering that the feared outcome was unlikely and/or not catastrophic; they intensify self-focus; they may increase feared symptoms; they can draw attention to feared symptoms; and they can also interfere with the social interaction, for example, not answering a question may be perceived as unfriendly, and so elicit less friendly reactions from others.

Empirical support for the causal role of self-focused attention and safety behaviours in adults comes from experimental studies that have manipulated these variables (see Piccirillo, Taylor Dryman [16] and Norton and Abbott [17] for reviews of safety behaviours and self-focused attention, respectively). Two studies manipulated self-focused attention and safety behaviours simultaneously. In the first study with a sample of adults drawn from an analogue population, McManus, Sacadura, & Clark [18] demonstrated that experimentally manipulating self-focus and safety behaviour use during a conversation task modulated participants’ experience of anxiety and appraisals of their performance, as well as affecting how the participant objectively came across to others. The second study evaluated the effects of this experimental manipulation with a clinical sample of adults as part of cognitive therapy treatment [19]. Patients felt more anxious, thought they appeared more anxious, and came across worse when they focused on themselves and used safety behaviours. This consistent finding was used in subsequent therapy sessions to encourage patients to shift to a more external focus of attention in everyday social interactions and to drop their safety behaviours in order to more effectively test their anxiety provoking expectations.

The question of whether these same processes are present and causally related to social anxiety in adolescents remains relatively unexplored. However, it cannot be assumed that the maintenance processes in adult and adolescent social anxiety are the same, due to reasons such as ongoing cognitive maturation [20], the changing social environment, and heightened sensitivity to social reward [21] during adolescence [10]. A small number of correlational studies examining the association between the two candidate processes and social anxiety symptoms were identified in a recent systematic review of the literature pertaining to the applicability of the Clark & Wells’ cognitive model in adolescents [10]. A moderate association between self-focused attention and social anxiety was reported in three of the four relevant studies [22–25], and a moderate to large association between safety behaviours and social anxiety was found in four studies [22, 23, 26, 27]. Taken together these findings suggest that self-focused attention and safety behaviours co-vary with adolescent social anxiety. Whilst the data is consistent with a causal account, experimental studies are needed in order to comprehensively test the hypothesis. To our knowledge, as yet no studies have been undertaken with adolescents.

Here, we describe an experimental study manipulating self-focus and safety behaviours during a conversation task in high and low socially anxious youth. The effects on self-reported anxiety and performance, conversation-partner ratings, and independent assessor ratings are examined. We tested three main hypotheses in the study: first, that that self-focus and safety behaviours would increase feelings and appearance of anxiety; second, that the detrimental effects of safety behaviours and self-focus would be evident in both high and low socially anxious adolescents, because the safety behaviours employed are typical of those with SAD [26]; and third, that self-focus and safety behaviours would undermine performance, as reflected in more critical judgements by conversation partners and independent observers.

The findings of this experimental study are consistent with the hypothesis that self-focused attention and safety behaviours are relevant to the maintenance of adolescent social anxiety. Participants felt more anxious and thought they looked more anxious in the ‘With’ compared to the ‘Without’ condition. They also thought they came across worse and that their negative predictions were more likely to have occurred. To a certain extent their fears were realised, in that the conversation partner and the independent observer rated them more critically, in terms of looking more anxious and being less likeable, when self-focused and using safety behaviours.

It is interesting to note that the detrimental effects of self-focus and safety behaviours were observed in both high and low anxiety groups. The finding indicates that focusing on oneself and using safety behaviours in social situations is unhelpful for adolescents in general, whether or not they are socially anxious. However, when we compare ratings of safety behaviour use and self-focus in social situations day-to-day, significant group differences were observed. It therefore seems that whilst using safety behaviours and focusing internally is unhelpful for all adolescents, young people who are more socially anxious tend to use them more in everyday life, and so this will mean that the adverse effects will only manifest for this population. Extending from this observation is the question of why some individuals adopt these psychological processes more than others. Longitudinal studies examining the temporal associations between negative social beliefs and safety behaviours and self-focused attention could test the hypothesis put forward by cognitive accounts of social anxiety that it is negative social schema that motivate the use of safety behaviours and self-focus (e.g. [12]).

Our findings provide evidence for mechanisms of adolescent social anxiety: safety behaviours and self-focus. We cannot draw conclusions about the extent to which effects are driven by self-focused attention and/or the use of safety behaviours, because both processes were manipulated together. This is because in reality it is difficult to conceive of an individual using common safety behaviours such as monitoring how they are coming across and rehearsing what they are going to say without focusing on themselves. Whilst it is difficult to manipulate safety behaviours without manipulating self-focus, future studies that examine the effect of manipulating focus of attention only during a social interaction task would be useful. This limitation perhaps highlights the interconnectedness of the processes [35] emphasised in the dominant cognitive behavioural models of social anxiety in adults (e.g. [11, 12]). Support for the idea that the processes are reciprocally related also comes from this study (see also [36]). Participants were asked whether or not they had experienced an image or impression of how they came across during each conversation. Despite no instructions relating to mental imagery, almost half of all participants (49%) experienced a spontaneous negative image of how they looked when they were self-focused and using safety behaviours. One participant described an image of themselves as “The weird kid sitting in the corner”, another as “Sweating, blushing, uptight, spoilt, posh”. This compares to only 7% (4/59) in the ‘Without’ condition. The finding aligns with the suggestion that self-focus increases awareness of internally generated information such as negative images and impressions [37].

Participants were instructed to use a common set of safety behaviours, based on those used in the study of McManus et al [18]. However, according to cognitive accounts of social anxiety, safety behaviours are highly idiosyncratic to individuals and to their specific fears. As a result, we cannot conclude from our findings that the use of any safety behaviours is detrimental, but rather that the use of this particular set of safety behaviours is. However, the specific instructions that we used for the safety behaviour manipulation were based on safety behaviours that are particularly commonly reported by both socially anxious adults [18, 19, 38] and adolescents [10, 27, 39]. These safety behaviours are also strongly correlated with self-reported social anxiety in those samples when the correlations are based on naturalistic use [22, 23]. In addition to this limitation, we note that conversation partners were on average eight years older than participants, which may limit generalisability of our findings to an extent, and future studies with similar-aged peers as conversation partners would be useful. Furthermore, single item measures are prone to random measurement error and so future studies could include multi-item measures.

Although the sample was not drawn from a clinical population, the average score of high social anxiety participants’ on a measure of social anxiety (LSAS-CA) was high (74.79 [28.44]) and the participant with the lowest LSAS-CA scored 29, which is above the suggested threshold (22.5) for distinguishing adolescents with social phobia and healthy controls [29]. Therefore, the findings of this study may well be pertinent to the task of developing therapeutic techniques for adolescents with SAD. Cognitive Therapy for adult SAD [40], includes a self-focused attention and safety behaviours experiment similar to the one in this study in session 2 of the treatment. Therapists use it to help patients discover the unintended consequences of the processes. This demonstration is later followed by attention retraining to help patients reduce self-focus and become more externally focused in social situations; and behavioural experiments to help patients test out their predictions in feared situations whilst dropping their safety behaviours and focusing on other people and their reactions. Our results suggest that also incorporating the self-focused attention and safety behaviours experiment and linked procedures into CBT protocols for adolescent social anxiety may be beneficial. Consistent with this suggestion, two outcome studies that used versions of the adult Cognitive Therapy for SAD protocol with adolescents have shown promising results [41, 42].

This study indicates that the use of safety behaviours and self-focus in social situations is unhelpful. The processes are problematic in a number of ways, including increasing anxiety, maintaining negative self-perceptions, prompting negative mental imagery, and contaminating social performance. This is consistent with cognitive models of social anxiety in adults that suggest specific psychological processes (social cognitions, negative imagery, self-focused attention, and safety behaviours) create interlocking reciprocal links that lock individuals into a cycle of social anxiety. Our study suggests that similar processes may operate in adolescents and point to potential opportunities for intervention.