Research and Practice in Couple Therapy

This study aimed to determine whether natural language patterns extracted from early couple therapy sessions can accurately predict premature therapy dropout. The study used a mixed quantitative–qualitative design involving 148 couples from Canada who participated in community, private, and university-based couple therapy settings. High-quality audio recordings of the first two therapy sessions were transcribed and preprocessed using advanced natural language processing techniques, including tokenization, lemmatization, turn-level segmentation, and affective, syntactic, and semantic feature extraction via transformer-based models. Communication variables such as emotional disengagement, interruption frequency, partner-focused pronoun use, and demand–withdraw sequences were quantified. Machine-learning models—logistic regression, random forest, gradient boosting, Bi-LSTM networks, and transformer architectures—were trained to predict dropout, defined as termination prior to session four without therapist-approved discontinuation. Model performance metrics included accuracy, precision, recall, F1 score, and ROC-AUC. SHAP values were used to interpret model-level decision patterns. Reflexive thematic analysis of therapist notes complemented quantitative findings to contextualize communication deficits. Inferential analyses revealed significant differences between dropout and treatment-completion groups across multiple linguistic variables, including higher negative affect, lower partner-focused pronouns, greater interruption frequency, and elevated demand–withdraw cycles among dropout couples (all p < .001). Transformer-based models achieved the strongest predictive accuracy (92%) and highest ROC-AUC (0.96), outperforming all traditional and neural baselines. SHAP interpretability demonstrated that emotional disengagement markers, interruption frequency, topic abruptions, and conversational asymmetry were the most influential predictors of dropout. Communication reciprocity declined over time in dropout couples, whereas it increased in treatment completers. Early-session communication deficits captured through natural language processing serve as powerful predictors of premature dropout in couple therapy. Incorporating automated linguistic assessment tools into routine clinical practice may enable earlier identification of at-risk couples and support targeted intervention strategies to reduce attrition.

The objective of this study was to determine whether deep neural networks can accurately predict couple therapy outcomes using only pre-treatment psychological and relational assessments. This quantitative predictive study analyzed pre-treatment data from 176 Canadian couples seeking therapy for relational distress, communication difficulties, or emotional disconnection. Participants completed standardized intake measures including relationship satisfaction, communication patterns, emotional symptoms, attachment orientations, and dyadic demographic variables. All data were preprocessed, normalized, and transformed into dyadic-level and discrepancy-level features. A deep neural network was developed using TensorFlow/Keras, optimized via hyperparameter tuning, and evaluated against baseline machine-learning models. The dataset was split into training, validation, and test subsets using a couple-level 70/15/15 partition to preserve dyadic independence. The deep neural network demonstrated superior predictive accuracy compared to random forest, support vector regression, and linear regression models, achieving an R² of .71 on the test set. SHAP analyses revealed that relationship satisfaction, demand–withdraw patterns, attachment avoidance, partner stress discrepancy, and constructive communication were the strongest predictors of therapy outcomes. Inferential patterns indicated significant non-linear interactions between emotional symptoms and communication variables, with higher improvement predicted for couples displaying lower avoidance, greater baseline cohesion, and smaller dyadic emotional discrepancies. Predicted-versus-actual outcome comparisons showed strong convergence, with minimal dispersion around the diagonal line of fit. Deep neural networks offer a powerful method for predicting couple therapy outcomes using intake assessments, capturing the complex non-linear dynamics inherent in relational functioning. By identifying key pre-treatment predictors such as satisfaction, communication patterns, attachment profiles, and dyadic discrepancies, these models can support personalized treatment planning and enhance clinical decision-making. The findings underscore the promise of computational approaches in advancing precision-based psychological interventions for couples.

The objective of this study is to develop and validate machine learning models capable of accurately identifying couples at early risk for emotional disengagement based on psychological, behavioral, and communication-related indicators. This predictive cross-sectional study included 156 couples (N = 312 individuals) from across Canada who completed validated measures assessing emotional disengagement, relationship satisfaction, conflict frequency, attachment dimensions, daily supportive behaviors, and communication responsiveness. Data were collected through secure online surveys, and dyadic datasets were prepared using actor–partner structures to preserve relational interdependence. Five machine learning algorithms—logistic regression, random forest, gradient boosting, support vector classifier, and a neural network model—were trained on cleaned and normalized datasets, with performance evaluated through accuracy, precision, recall, F1 score, and area under the ROC curve. Cross-validation procedures ensured the robustness and generalizability of the models. Inferential analyses demonstrated that gradient boosting achieved the highest predictive performance (AUC = 0.94), followed closely by neural networks (AUC = 0.93) and random forests (AUC = 0.91). All models significantly outperformed logistic regression and support vector classifiers, indicating the superiority of non-linear approaches for capturing subtle relational patterns. Emotional withdrawal was the strongest predictor across all models (p < .001), followed by daily supportive behaviors, communication responsiveness, attachment avoidance, and conflict frequency. Demographic variables showed no significant predictive contribution (all p > .05). Confusion matrix analyses revealed that gradient boosting produced the lowest false-negative rate, confirming its utility for early detection. The study demonstrates that machine learning models, particularly gradient boosting and neural networks, can accurately detect early signs of emotional disengagement in couples by integrating relational, emotional, and behavioral indicators. These findings highlight the potential of computational approaches to support preventive interventions and enhance clinical assessment in couple therapy.

This study aimed to examine the predictive roles of narcissistic traits and emotional coldness in determining levels of marital empathy among married adults. A correlational descriptive design was employed using a sample of 393 married individuals from Tunisia, selected based on Morgan and Krejcie’s sample size determination table. Participants completed standardized self-report questionnaires measuring narcissistic traits, emotional coldness, and marital empathy. Data were analyzed using SPSS version 27. Descriptive statistics were calculated, followed by Pearson correlation to examine bivariate associations and multiple linear regression to assess the predictive power of independent variables on marital empathy. Assumptions for regression analysis were tested and confirmed prior to analysis. Pearson correlation results revealed significant negative relationships between marital empathy and both narcissistic traits (r = -0.42, p < .01) and emotional coldness (r = -0.58, p < .01). A moderate positive correlation was also found between narcissistic traits and emotional coldness (r = 0.46, p < .01). The regression model was significant, F(2, 390) = 126.45, p < .001, accounting for 40% of the variance in marital empathy (R² = 0.40). Both narcissistic traits (β = -0.29, p < .001) and emotional coldness (β = -0.45, p < .001) emerged as significant negative predictors, with emotional coldness having a stronger effect. The findings underscore the detrimental effects of narcissistic traits and emotional coldness on marital empathy. Emotional coldness, in particular, is a stronger predictor of empathic deficits in marital relationships. These results highlight the need for interventions that target emotional responsiveness and personality-driven barriers to empathy in couples therapy and relationship counseling.

This study aimed to investigate the predictive roles of spiritual closeness and life goals alignment in marital identity fusion among married individuals in Egypt. A correlational descriptive design was employed with a sample of 400 married participants selected based on the Morgan and Krejcie sampling table. Standardized instruments were used to measure marital identity fusion, spiritual closeness, and life goals alignment. Data were analyzed using Pearson correlation and multiple linear regression via SPSS version 27. All assumptions of normality, linearity, multicollinearity, and homoscedasticity were tested and met prior to conducting inferential analyses. Pearson correlation analysis showed that marital identity fusion was positively and significantly correlated with both spiritual closeness (r = .64, p < .001) and life goals alignment (r = .59, p < .001). The multiple regression model was statistically significant, F(2, 397) = 182.71, p < .001, explaining 48% of the variance in marital identity fusion (R² = .48). Both spiritual closeness (β = .44, t = 7.83, p < .001) and life goals alignment (β = .38, t = 7.14, p < .001) were significant predictors, indicating that higher levels of these relational dimensions are associated with stronger psychological identity integration between spouses. The findings underscore the importance of spiritual closeness and life goals alignment in fostering marital identity fusion. These variables contribute significantly and independently to the psychological merging of partners in marital relationships. The results highlight the value of integrating spiritual and aspirational congruence into marital counseling and educational interventions to enhance marital cohesion and stability.

This study aimed to evaluate the effectiveness of expressive arts therapy in enhancing marital empathy and emotional stability among married individuals. A randomized controlled trial was conducted with 30 married individuals (15 per group) in Georgia. Participants were randomly assigned to either an experimental group receiving an eight-session expressive arts therapy intervention or a control group placed on a waitlist. Each session lasted 60–75 minutes and integrated multiple modalities including visual arts, movement, music, and storytelling. Assessments were conducted at three time points: pretest, posttest, and five-month follow-up. Standardized tools were used to measure marital empathy and emotional stability. Data were analyzed using repeated measures ANOVA with Bonferroni post-hoc tests, and all assumptions were met. Statistical analysis was conducted using SPSS-27. Significant time × group interactions were observed for both marital empathy (F(2,54) = 20.18, p < .001, η² = .436) and emotional stability (F(2,54) = 18.44, p < .001, η² = .413), indicating that the experimental group experienced greater improvement over time compared to the control group. Bonferroni post-hoc comparisons showed significant increases from pretest to posttest and pretest to follow-up in both marital empathy (p < .001) and emotional stability (p < .001), with no significant decline at follow-up, suggesting that the therapeutic gains were maintained. Expressive arts therapy proved to be an effective and sustainable intervention for improving marital empathy and emotional stability. The results support the integration of creative, multimodal therapeutic approaches into marital counseling programs and highlight the enduring benefits of symbolic, embodied, and narrative-based interventions for couples’ emotional health.

This study aimed to evaluate the effectiveness of a structured Distress Tolerance Program on improving marital adjustment and reducing negative affect in married individuals. A randomized controlled trial was conducted involving 30 married participants from Armenia, who were randomly assigned to either an intervention group (n = 15) receiving a 10-session Distress Tolerance Program or a control group (n = 15) receiving no intervention. Standardized tools—the Dyadic Adjustment Scale (DAS) and the Negative Affect subscale of the PANAS—were administered at three time points: pre-test, post-test, and five-month follow-up. Data were analyzed using repeated measures ANOVA and Bonferroni post-hoc tests with SPSS-27. Assumptions for normality, homogeneity, and sphericity were confirmed prior to inferential testing. Results demonstrated significant time × group interaction effects for both marital adjustment (F(2, 56) = 27.22, p < .001, η² = .51) and negative affect (F(2, 56) = 26.26, p < .001, η² = .48). Bonferroni post-hoc comparisons indicated significant improvements in marital adjustment and reductions in negative affect from pre-test to post-test and from pre-test to follow-up (all p < .001) in the intervention group. No significant changes were observed between post-test and follow-up scores, suggesting the intervention effects were sustained over time. The findings support the efficacy of distress tolerance training as a targeted psychological intervention for enhancing marital adjustment and reducing negative affect. The program’s long-term benefits highlight its potential for use in clinical and marital counseling settings, especially in culturally sensitive contexts where emotional suppression and relational conflict are prevalent.

This study aimed to examine the predictive roles of partner dependability and emotional support in relational commitment among individuals in romantic relationships. The research employed a correlational descriptive design with a sample of 380 participants from Iraq, selected based on the Morgan and Krejcie sample size table. Standardized tools were used to assess relational commitment, perceived partner dependability, and emotional support. Data were analyzed using SPSS-27 software, employing Pearson correlation to evaluate the relationships between variables and multiple linear regression to test the predictive power of the independent variables on the dependent variable. The results revealed significant positive correlations between relational commitment and both partner dependability (r = .68, p < .01) and emotional support (r = .59, p < .01). Multiple regression analysis showed that the overall model was significant, F(2, 377) = 168.29, p < .001, explaining 47.2% of the variance in relational commitment (R² = .472). Both partner dependability (β = .46, t = 9.87, p < .001) and emotional support (β = .34, t = 7.51, p < .001) were found to be significant predictors, with partner dependability having a stronger predictive value. These findings suggest that relational commitment is substantially influenced by both the perceived reliability and emotional responsiveness of one’s partner. The study highlights the importance of fostering consistent and supportive behaviors within romantic relationships to enhance commitment levels. The results have implications for relationship counseling and education programs, particularly within culturally specific contexts like Iraq.