Precision Livestock Farming (PLF) is increasingly recognized for its potential to improve the health and welfare of farm animals, their productivity, and environmental sustainability. Nevertheless, the critical transition of PLF from a theoretical research concept to practical field implementation remains essential for realizing its full potential. This study undertakes a scientometric review of PLF and its application in the monitoring of farm animal welfare, covering the period from 2006 to 2025. The study employs a mixed-corpus scientometric approach to concurrently assess trends in PLF publications (n = 1,594) and patents (n = 3,239), revealing a strong co-evolutionary relationship (r = 0.913, 95% CI 0.79–0.97, p < 0.001) between academic and industrial PLF activity, with annual growth rates of 32.2% and 20.2%, respectively. The analysis identifies key research subfields and traces the evolution of PLF themes across three overlapping phases: a hardware validation phase (2006–2015), a welfare outcome validation phase (2016–2020), and an artificial intelligence integration phase (2021–2025). The study underscores the importance of integrating scientific literature and patent data for comprehensive insights into PLF’s role in enhancing farm animal welfare and highlights persistent gaps between proof-of-concept research and commercially deployed, welfare-validated systems.

Skill is the ability to do a challenging behaviour well. We examined how contest skill influences contest success, costs and whether skilful behaviour enhances welfare. We measured skill across three domains: accuracy, appropriateness (selecting suitable agonistic tactics when the optimal choice varies) and efficiency, alongside vigour, sex and body weight. Skill was weakly correlated across domains. Winners were heavier relative to their opponent, displayed greater vigour and were more skilful at blocking, but other skill measures did not predict contest win/loss outcome. Appropriate blocking by winners reduced the number of lesions received by reducing exposure to attacks, suggesting it can both reduce costs and improve competitive success, with potential welfare benefits. Losers received more lesions when they adopted appropriate postures after submission; however, this unambiguous submission may have resulted from more costly contests. For winners, being heavy relative to the opponent tended to reduce skin lesions received, but otherwise, having a weight advantage did not reduce contest costs. Fighting with increased vigour led to a considerable increase in contest costs, particularly in losers. Compared to other resource-holding potential traits, skill has moderate effects on winning and injuries but nevertheless modulated energetic costs of fighting.

Affiliative behaviours in pigs can enhance group cohesion and lower stress levels, ultimately improving individual welfare. Individual factors such as dominance rank, sex or kinship may play a key role in shaping the expression of social behaviours, but there is a lack of knowledge on the contribution of these variables. The aim of this study was to identify social behavioural profiles in pigs, based on putative affiliative behaviours, and evaluate the extent to which dominance rank, sex, and kinship influence their expression. Agonistic interactions were recorded on 212 male and female domestic pigs (Sus scrofa domesticus) to calculate dominance ranks within 16 groups. Based on this, 96 pigs (six pigs per group) were selected for observations on detailed social nosing behaviours, allogrooming, spatial proximity and social play. Principal components analysis was used to assess the presence of behavioural profiles, followed by mixed model analysis to evaluate the influence of individual factors on each principal component (PC). Snout contact constituted the majority of interactions and was exhibited by all pigs. Lying in body contact and snout-snout proximity were also frequent and were expressed by more than 95% of individuals. Allogrooming and social play were observed in 29.2 and 33.3% of pigs, respectively, and represented less than 1% of the total interaction frequency. Three PCs had eigenvalues > 1 and together explained 60.9% of the variance. The PCs related to social contact (PC1), proximity (PC2) and social engagement (PC3). Sex, dominance status and kinship had no effect on PC1 or PC3, but sex and kinship had a limited effect on PC2, with entire males showing more snout proximity than females (P < 0.001) and pigs showing less snout proximity behaviours towards their kin (P = 0.044). This study shows that the expression of putatively affiliative social behaviours can be clustered into profiles and is under commercial settings only marginally influenced by individual factors such as dominance and kinship, suggesting their general relevance to pigs' social life.

There are several examples of best animal husbandry practices that are not adopted, leading to animal welfare compromises. Bridging this gap between advice and human behaviour is crucial in helping drive improvements in animal welfare. Inappropriate feeding of pregnant cows is common and associated with compromised health and welfare. Obesity and leanness can cause calving difficulty and reduce the vigour of newborn calves. One way to offset the problems associated with body condition extremes is to adopt body condition scoring (BCS) by hand. Knowing each animal’s condition helps the farmer identify ‘at risk’ cows leading to better feeding decisions and improved health and welfare. Despite the significant benefits of BCS, very few farmers routinely adopt this practice, relying more upon a visual assessment of condition. Some farmers also report that they do not BCS by hand, or by eye. The current study identified the key barriers and drivers of BCS by hand to develop an evidence-based intervention designed to encourage more adoption. We propose that human behaviour change frameworks, such as the Behaviour Change Wheel (BCW), present the opportunity to address other animal welfare issues where best management practices are rarely adopted. We also recommend that an interdisciplinary team of animal welfare and social scientists are best positioned to develop human behaviour change interventions that will more likely lead to tangible, persistent and positive change.

Social network analysis (SNA) provides a means of understanding animals' agonistic behaviour in a group. The aim of this study was to use SNA to characterise how individual cognitive performance affects agonistic behaviour. Using 175 pigs, we hypothesised that their choice of opponents would be affected by their ability to discriminate spatial information and to adapt their behaviour when cues were reversed. A spatial discrimination test was conducted; left and right locations were assigned as positive (food reward) and negative (fan) and each pig's learning speed was recorded. The cues were then reversed, and we tested whether pigs adjusted their behaviour. At age 14 weeks, pigs were regrouped into 14 groups, and their behaviour recorded for 5h, from which weighted and unweighted networks were constructed. Skin lesions were counted after 24h, 1 week and 2 weeks. Males delivered more aggression, and heavier pigs were involved in more aggression. Betweenness centrality (a network position linking otherwise unconnected individuals) increased with network size and decreased with body weight. Passing the reversal learning test predicted more involvement in unilateral aggression. The current study therefore shows links between cognitive performance and aggression and advances the understanding of social network analysis in the context of animal welfare.

During behavioral trade-offs, individuals have to decide whether to express a behavior which may lead to a reward or potential costs when engaging in a risky situation. Social integration forces animals to make such trade-offs. We hypothesized that animals predominantly demonstrate nontactile behavior and hence less tactile behavior in a high-risk context such as during social integration, while using tactile behavior more than nontactile in less risky situations such as under social stability. Pigs (Sus scrofa domesticus) typically are in close physical contact to each other, but physical contact also relates to increased aggression. We investigated 18 groups (142 pigs) across different phases of social stability, thereby observing snout proximity and snout contact. Additionally, aggression (reflecting costs) and growth performance (reflecting benefits) were measured. Data were analyzed using mixed models while accounting for group stability. Snout proximity was indeed most frequent during social instability and reduced as stability increased, while snout contact remained more constant. The high occurrence of snout proximity during social instability suggests conflict avoidance and thus risk aversion. Animals that showed more frequent snout proximity grew slower, while initiators and recipients of frequent snout contact had a better growth performance. The causality of these effects cannot be ascertained, but it is possible that slower growing, and thus weaker individuals may have made a behavioral trade-off by choosing proximity rather than contact during social instability. The results further emphasize the importance of distinguishing between nuances in behavior.

Social relationships in farm animals, including pigs, have become a focus of research, yet long-term studies are scarce. Pigs, being highly social animals, offer an excellent model to explore social preferences over time. This study aimed to investigate social preferences in female pigs across life stages by observing a group of ten gilts over one year, with each season serving as an assessment point. Social interactions (allogrooming, snout-body, and snout-head contact) were recorded through live and video observations, totaling 396 h per animal. Social Network Analysis (SNA) assessed group cohesion using measures of density, reciprocity, and degree centralization. Monte Carlo simulations, half-weight association index (HWI) and the Quadratic Assignment Procedure (QAP) were used to evaluate social preferences and their recurrence across seasons. Results showed high density (0.95) and reciprocity, with weak centralization (in-degree 0.19, out-degree 0.27), indicating uniform distribution of social interactions. On average across the four seasons, 5.8 % of connections were strong, 35.7 % weak, and 58.5 % non-preferential. Social preferences correlated modestly between autumn and winter, but not with summer and spring. This study confirms previous findings that only a small proportion of pigs form non-random associations within a group. Social preferences lasted for a maximum of two seasons, likely influenced by pregnancy and transitions from gilt to adult sow, which resulted in temporary withdrawal from the group.

Background: The social interactions of farm animals affect their performance, health and welfare. This proof-of-concept study addresses, for the first time, the hypothesis that applying social network analysis (SNA) on AI-automated monitoring data could potentially facilitate the analysis of social structures of farm animals. Methods: Data were collected using automated recording systems that captured 2D-camera images and videos of pigs in six pens (16-19 animals each) on a PIC breeding company farm (USA). The system provided real-time data, including ear-tag readings, elapsed time, posture (standing, lying, sitting), and XY coordinates of the shoulder and rump for each pig. Weighted SNA was performed, based on the proximity of "standing" animals, for two 3-day period-the early (first month after mixing) and the later period (60 days post-mixing). Results: Group-level degree, betweenness, and closeness centralization showed a significant increase from the early-growing period to the later one (p < 0.02), highlighting the pigs' social dynamics over time. Individual SNA traits were stable over these periods, except for the closeness centrality and clustering coefficient, which significantly increased (p < 0.00001). Conclusions: This study demonstrates that combining AI-assisted monitoring technologies with SNA offers a novel approach that can help farmers and breeders in optimizing on-farm management, breeding and welfare practices.

Social interactions of farm animals affect their performance, health and welfare. The recent advances in AI-automated monitoring technologies offer digital phenotypes, at low-cost, that record the animals in real-time. This proof of concept study addresses, for the first time, the hypothesis that applying social network analysis (SNA) on automated data could potentially facilitate the analysis of social structures of farm animals. Data was collected using automated recording systems that captured 2D camera images and videos of pigs in six pens (16 to 19 animals each) on a PIC breeding company farm (USA). The system provided real-time data, including ear-tag readings, elapsed time, posture (standing, lying, sitting), and XY coordinates of the shoulder and rump for each pig. Weighted SNA was performed, based on the proximity of standing animals, for two 3-day periods, the early growing period (first month after mixing) and the later period (60 days post-mixing). Group level degree, betweenness, and closeness centralization showed a significant increase from the early growing period to the later one (p<0.02), highlighting the pigs social dynamics over time. Largest clique size remained unchanged (p=0.28), but the number of maximal cliques significantly decreased from the early to late growing period (p=0.007). Individual SNA traits were stable over these periods, except for closeness centrality and clustering coefficient which significantly increased (p<0.00001). This study demonstrates that combining AI-assisted monitoring technologies with SNA offers an efficient, real-time approach to gain novel insights into animal social interactions. This approach can optimize on-farm management or breeding practices, leading to improved animal performance, health, and welfare. ### Competing Interest Statement The authors have declared no competing interest.

During the formation of new social groups, temporal variations in behavioural associations between individuals can provide insight into the role of behaviours during group formation. While social behaviour during the establishment of new groups has been studied, there is a lack of knowledge on how non-agonistic social patterns change across time. The aim of this study was, therefore, to examine temporal variation in behavioural associations between individuals during the formation and maintenance of social relationships between conspecifics. This was studied in 15 mixed-sex groups of commercial pigs (n = 118 pigs; 8 pigs per group), which were regrouped at the start of the experiment (at weaning). They were studied between 4 and 11 weeks of age to capture variation in group stability. We focused exclusively on snout-directed behaviour given its role in conspecific recognition and affiliative interactions, whereby particularly snout-to-snout contact may contribute to the development of social relationships. Social network analysis (SNA) was used to investigate temporal associations. The results show that pigs made frequent snout contact (avg. 33 times / 15 min.) and that interactions were relatively more affiliative than aggressive (tenor range: 0.52 - 0.61), and were more affiliative in the high as compared to medium social stability phase (p = 0.02). As group integration progressed, the number of social partners involved in snout contact decreased, while the frequency of snout contact per individual increased. There was no evidence of non-random social preferences and no evidence of centralised associations (degree centralisation range: 0-0.3). Pigs showed more snout contact with non-littermates than littermates (i.e. a heterophilic association based on litter origin; assortativity range: -0.34 to -0.08) and between individuals with different early social experiences (assortativity range: -0.45 to -0.07) across all integration phases. Additionally, males initiated contact more frequently than females, whereas females occupied more central positions within the social network. These behavioural processes, which support the formation and maintenance of social relationships, show that non-agonistic behaviours such as snout contact have a prominent role in the social dynamics of pigs.

Negative social behaviors represent a welfare and economic problem for farm animals worldwide. The time-consuming nature of observing behavior on a large scale means that social problems are not visible until their negative physical effects are advanced. However, identifying the key initiators or propagators of fighting and/or biting may not be possible by observing injury alone. Therefore, in this study, we investigated the possibility of constructing and analyzing social networks from AI-assisted automated monitoring data in pigs and the feasibility of using spatial proximity association as an indicator of harmful social interactions. Data were collected using automated recording systems that captured 2D camera images and videos of 6 pens of pigs (16-19 per pen) on a PIC breeding farm (USA). The system records continuous video footage with the associated real-time ear-tag ID, elapsed time, posture (standing, lying, sitting) and XY coordinates of the shoulder and rump for each pig. The validation of automated identity, posture and location records show 97-100% agreement with human observations (Agha et al., 2024). Pig movements were recorded from 10:00 to 19:00h for 6 days; 3 days immediately after regrouping and 3 days, 60 days after regrouping. Proximity data was used to create weighted social networks. Group level metrics (degree, betweenness, and closeness centralization) significantly increased from the early to late growing periods (p< 0.02), highlighting that inequality in proximity between pigs increased over time. Largest clique size remained unchanged (p=0.28), but the number of maximal cliques (fully connected subgroups) significantly decreased from the early to late growing period (p=0.007). Individual SNA traits were mostly stable over these periods. Measuring the behavior of prominent individuals during the time they are in proximity will allow targeting of management interventions to improve welfare outcomes. We tested an initial dataset as proof of concept that proximity signatures can be used to identify aggression. Video footage of two pens of 19 pigs were observed and 37 mutual fighting bouts were identified. Proximity matrices were calculated for each pen using shoulder XY location, for the duration of the bout, lasting 2-42 s (median 5.0s). 81% of fighting dyads were identified as in proximity (< 0.5m) compared with 7% (468/6290) of non-fighting dyads, χ2=7.0, p=0.008. Of the dyads in proximity, fighting dyads were in proximity for over twice as much of the interval (median: Q1-Q3); (92: 31.4-96.1%) as non-fighting dyads (44.3: 16.8- 86.1%), p< 0.001 Refinements to improve sensitivity and specificity to diagnose and characterize aggressive behavior from larger samples of proximity data are ongoing. This study demonstrates that integrating SNA with automated data reveals novel insights into pigs’ social interactions and identifies a signature of aggressive encounters using proximity. That could offer promising applications in breeding and management of farmed animals.

IntroductionThis study explores the Precision Livestock Farming (PLF) technology perceptions and data needs of off-farm swine industry stakeholders. The aim was to increase our understanding of PLF’s real-world applicability beyond farm operations. MethodsUsing focus group discussions, five professionals—spanning government official, animal scientists, food processors, and retail representatives—offered insights on ideal data types and practical concerns associated with PLF adoption. Using the Nominal Group Technique (NGT), we determined that participants have unique data needs, with no clear consensus on data priorities for PLF. We conducted a second focus group following normal focus group protocols, allowing us to further explore participants’ PLF priorities, nuanced perspectives, and shared beliefs. Results and discussionWe identified five themes: “To Split the Check or Not to Split the Check; Knowing the Benefits is Key; Reconciling Profit and Welfare in PLF; What Use is PLF to the Animal Anyway? and The Value and Caveats of PLF Data. The benefits of PLF data to participants were closely tied to clear cost-sharing structures, meaningful benefits for diverse stakeholders, and assurances about data control. Stakeholders voiced concerns around financial feasibility, ethical implications, and practical barriers in terms of data management. Overall, addressing these complex but interrelated needs and concerns by other stakeholders can make data generated by PLF useful beyond the farm and provide additional incentives to advance PLF adoption in the swine industry. This finding may provide actionable insights to inform strategies that support both the technological advancement and ethical sustainability of PLF in animal agriculture.

The objective was to determine the effects of dietary standardized ileal digestible (SID) lysine (Lys) levels and SID tryptophan (Trp) to Lys ratios on the growth performance of late-nursery maternal barrows. A total of 2,293 barrows (PIC Camborough, initially 11.9 ± 0.35 kg) were used in a 28-day trial with 96 mixed-sex pens in two rooms (48 pens/room), 16 pens/treatment, and 23 to 25 pigs/pen. Pens were blocked by body weight (BW) and randomly allotted to 1 of 6 treatments in a 2×3 factorial arrangement. Treatment factors were: 1) Dietary SID Lys levels: meet PIC SID Lys recommendation at 1.234% (PIC LYS) or below PIC SID Lys recommendation at 0.988% (BELOW LYS); 2) Dietary SID Trp to Lys ratios: 21.0, 18.5, and 16.0. Data were analyzed using a linear mixed model in R Studio (Version 3.5.2, R Core Team; Vienna, Austria). Dietary SID Lys levels, dietary SID Trp to Lys ratios, and their interaction were included as fixed effects, and room and weight block were included as random effects in the model. Pigs fed with PIC LYS diets showed significantly improved average daily gain (ADG; 672 vs. 594 g; P < 0.001), average daily feed intake (ADFI; 1227 vs. 1179 g; P < 0.001), gain-to-feed ratio (G:F; 550 vs. 508 g/kg; P = 0.002), and greater amount of SID Lys intake (22.5 vs. 19.5; P < 0.05) or Trp intake (4.2 vs. 3.6; P < 0.05) per kg of BW gain comparing to BELOW LYS diets. Significant interactive effects were observed between dietary SID Lys levels and dietary SID Trp and Lys ratios on final BW, ADG, ADFI, and G:F (P < 0.05; Table 1). For final BW and ADG, when feeding PIC LYS diets, decreasing dietary SID Trp to Lys ratios increased final BW and ADG (quadratic, P < 0.05); but when feeding BELOW LYS diets the decreasing ratios reduced final BW and ADG (quadratic, P < 0.05). For ADFI, when feeding PIC LYS diets, there was no evidence that decreasing dietary SID Trp to Lys ratios impacted ADFI (P > 0.05); but when feeding BELOW LYS diets the decreasing ratios reduced ADFI (quadratic, P < 0.05). When feeding PIC LYS diets, the decreasing dietary SID Trp to Lys ratios decreased and then increased G:F (quadratic, P < 0.05); but when feeding BELOW LYS diets, the decreasing ratios increased and then decreased G:F (quadratic, P < 0.05). In conclusion, late-nursery maternal barrows fed the PIC LYS diet had improved growth performance compared with those fed BELOW LYS diet; and decreasing dietary SID Trp to Lys ratios from 21.0 to 16.0 had deleterious impacts on growth performance when dietary SID Lys level was below PIC recommendation, but not when dietary SID Lys level met PIC recommendation.

Acceptable animal welfare is an integral part of sustainability. Selective breeding for improved animal welfare can benefit the economic and environmental aspects of pig farming, as well as being of direct benefit to the animal itself. Several traits have major welfare consequences but have proved difficult to improve through management change alone. Here we consider how past selection for productivity has affected welfare and give three examples of the state of the art in selective breeding aimed at improving welfare traits in their own right. Selection for complex welfare-relevant traits poses practical, economic, and ethical challenges. Current and emerging innovations will significantly reduce the economic and practical barriers to breeding and allow efficient selection for traits that previously have been too expensive to record. Examples will be given of the new phenotyping techniques and genetic methodologies that are expanding the range of welfare traits that selection pressure can be exerted upon.

Social touch is an important aspect of social relationships and has a major influence on development and health. However, in many species the occurrence and function of social touch is unknown. Pigs have frequent physical contact but this behaviour is largely unexplored. The aim of this study was to investigate the undisturbed variation in physical contact between pigs, and to assess diurnal and seasonal influences. A stable group of ten Pu & lstrok;awska sub-adult female pigs was observed for 406 h across four seasons during the day and night, by continuous observations on an individual level (406 h / pig). They were housed indoors (112 m2 pen) on straw bedding. The ethogram distinguished the amount of surface contact between pigs when lying, the orientation to others, social nosing, other non-agonistic social behaviour and agonistic behaviours. Resting location within the pen was recorded 48 times per pig, and dominance relationships were calculated from agonistic interactions. Data were analysed with mixed models accounting for repeated observations. Pigs spent on average 40 % of their time lying in body contact, most often lying with their extremities in contact (71 %), followed by lying in partial body contact (16 %) or full body contact (13 %) and were frequently nosing the head and body of others. The duration of lying in any type of contact, as well as agonistic behaviour, was influenced by season, with the longest durations in autumn. In summer, the duration of partial body contact was lowest, but full body contact was unaffected by season. Nosing behaviour remained constant throughout the year. Pigs lay in contact more during the night, while showing more social behaviours during the day. Pigs mostly lay in nonparallel orientation or head-to-head, but clearly least in the head-to-tail orientation. Season influenced the frequency of lying headto-head and head-to-tail, but not lying nonparallel. The coefficient of variation of the lying location was influenced by season. Allo-grooming, mounting, and nudging were shown infrequently and mostly by specific individuals. In conclusion, when at a large space allowance, pigs spend nearly half of their time in body contact, even during the higher temperatures in summer. This shows that social touch, including affiliative behaviour, has an important role in pigs' social life, and remains largely unaffected by external influences.

Losing aggressive contests may impact survival, reproductive success and animal welfare. Previous experience plays an important role in shaping contest behaviour, but less is known about how individual variation in learning abilities influences contest dynamics and resource-holding potential. Here, we investigated whether learning performance (acquisition learning and reversal learning) in domestic pigs, Sus scrofa, predicts the outcome of a contest against an unfamiliar opponent. While acquisition learning speed did not predict contest outcome, pigs that successfully learned the reversal were more likely to win the contest than pigs that failed to learn the reversal. As expected, weight difference between opponents was also an important factor in predicting contest outcome. Our results suggest that cognitive flexibility may confer an advantage in contests, unless pigs already have a substantial weight advantage over their opponent. These findings advance our understanding of the role of cognitive processes in animal contests and suggest that promoting cognitive flexibility may reduce the potential welfare impacts arising from stressful social defeat. Further research is required to determine whether cognitive flexibility influences assessment strategy and allows pigs to resolve contests with fewer costs. (c) 2024 The Author(s). Published by Elsevier Ltd on behalf of The Association for the Study of Animal Behaviour. This is an open access article under the CC BY license (http://creativecommons.org/licenses/ by/4.0/).

Leadership is a risky behaviour that can impact individuals and groups. Leaders, i.e. individuals who perform or initiate a task while other individuals in the group follow, have been studied in different contexts, but there is still a lack of understanding on the role of individual characteristics that may predispose them to become leaders, such as dominance and personality. In particular, the characteristics of leaders in domestic animal populations has been poorly examined. We studied leadership within 32 groups of young pigs (Sus scrofa domesticus, n = 366 individuals). Leadership was assessed during a group-based fear test (Human Approach Test) which was repeated three times. The first individual per group to touch the person was identified as leader. We assessed repeatability of leadership and characteristics of leaders as compared to followers. Leadership was marginally repeatable, with 6 out of 26 groups having a consistent single leader across all tests. Females had odds 4.13 times greater than males of being a leader, while there was no effect of body weight (a proxy of dominance) or coping style on leadership. The results indicate a similarity with wild populations, in which females lead the herd even though the males, which are superior in body weight, are often dominant.