Quality Of Dialogue Research Articles

Safety first: the hidden curriculum of whiteness in race-conscious professional learning

ABSTRACT Applying the analytic lens of critical whiteness, we examine the relationship between facilitation structures and the quality of racial dialogue in educator professional development. We draw on data from a five-session virtual ‘antiracist reading group’ in a rapidly diversifying U.S. district, convened and facilitated by a White district leader. Observed discussions tended towards the superficial and did little to challenge participants’ existing worldviews. We argue that the leader’s facilitation decisions characterised a ‘hidden curriculum’ of safety and comfort that inhibited participants’ development. These moves were further shaped by and reified persistent manifestations of whiteness. We offer implications for the facilitation of antiracist professional learning, equity leadership, broader policies related to equity, and future research.

A method and approach for evaluating coparenting events during couples group interventions.

When interventionists stimulate productive father-mother dialogues around coparenting, there are numerous potential benefits for families. Families stand to benefit from more positive involvement of fathers with both coparents and children, key contributors to healthy child developmental outcomes. In this report, we introduce a new strategy and rating system for helping practitioners and supervisors assess the nature and quality of coparenting-related dialogues and conversations in the context of couples group interventions. The system derives from analysis of 24 relationship-enhancement groups, 13 enrolling English-speaking couples and 11 enrolling Spanish-speaking couples, all parents of young children. All groups were co-led by a male-female team explicitly trained to focus on marital and parenting themes and supervised to address couples issues - not coparenting issues explicitly. All co-leaders spoke the native language of group participants. We documented how frequently coparenting events occurred, and how the nature and quality of events varied within and across groups. Overall, in both English- and Spanish-speaking groups expressly assembled to focus on marital and parenting issues, coparenting events occurred relatively infrequently. At the same time, both mothers and fathers appeared motivated to raise and discuss issues associated with their coparenting, and extended discussions about coparenting issues broached by the parents blossomed in approximately 37% of all instances. Process-oriented (rather than didactic) co-leader responses appeared especially helpful in scaffolding prolonged coparenting discussions. We propose that use of the system as a training, supervision and self-assessment tool can help clinicians become more consciously aware of how well their interventions succeed in promoting and scaffolding coparenting conversations during group interactions.

Aware and unaware- stereotypes and gender scripts in family narratives in the process of education

The aim of the article is to discuss the issues of shaping gender roles in children of early school age, taking into account the importance of stereotypes and gender scripts in this process.First of all, the basic concepts of roles, stereotypes and scripts referring to gender were presented, then I briefly reconstructed the basic assumptions of theories explaining the process of shaping a child's gender identity, in the second part of the considerations I discuss the most common patterns of female and male roles in Polish culture and present their relationships with the construction of identity, at the end I shared information on what behaviors should be avoided and how can we replace them so as not to disturb the formation of the child's ideas about functioning in gender roles. I am looking for answers to questions important from the research point of view: what role does communicative knowledge play in the process of shaping children's ideas about gender roles, and what role does conjunctive knowledge (experience) play? Is it possible to avoid stereotyping that comes from the dichotomy of gender roles in interactions with a child? How do images of gender roles become scripts? What is the significance of interference of messages from different environments (family, school, peer group) for the formation of a child's gender identity?Finally I emphasize the importance of both the narrative and dialogical character of education as a process of conscious influence on the formation of the child's ideas about gender roles (communicative knowledge), but also the broader impact of socialization processes, including intergenerational transmission (knowledge/conjuctive experience).

A importância do aprofundamento teórico-metodológico na formação docente e nas produções de materiais didáticos dialógicos no curso de Letras

The Bakhtinian approach has been present in Brazilian official curricular documents since the 1990s. However, its pedagogical appropriation has been guided by the linguistic structure to the detriment of social interaction (Faraco, 2009), demanding efforts in Portuguese school subject teacher training. In this article, the objective is to show how the dialogic discourse theory deepening can contribute to teaching materials production, based on Portuguese language major training experience at the University of São Paulo in 2020. In this experience, the theoretical-methodological approach includes the concepts of speech genres (Bakhtin, 2016 [1952-1953]) and theme (Volóchinov, 2018 [1929]) and on the production of didactic proposals aligned with the Base Nacional Comum Curricular (BNCC) (Brasil, 2018) and with the Sustainable Development Goals (SDGs) (Unesco, 2017). In this work, we analyze the proposal “Gênero do discurso e produção de texto: editorial” [“Speech genres and text production: editorial”], identifying the authors' observance of Bakhtinian discursive referents: i) sphere/field of human activity; ii) speech genre; iii) its relative stability; iv) multiple voices in statements; v) thematic totality. The results indicate dialogical quality in the material with the presence of elements that express social dynamics, confirming the relevance of theoretical deepening and its practical application in undergraduate teacher training.

Mitigating emotional barriers to feedback encounters and dialogue (in law schools)

ABSTRACT This article develops a tripartite typology categorising how negative emotions act as barriers to feedback encounters and dialogue. It draws on 11 semi-structured interviews with students and staff on a non-embedded writing support initiative implemented in the Law Department at the University of Manchester. Our findings reveal negative emotions inhibit feedback dialogue in three ways: accessing written feedback; accessing feedback dialogue; and the quality of feedback dialogue. We further suggest how non-embedded writing support can mitigate these emotional barriers, highlighting the need for educators to reflect on the emotional needs of their students in feedback processes.

Measuring the quality of philosophical dialogue: a high-inference rating instrument for research and teacher education

Various studies have shown that philosophizing with children at school can have a positive effect on cognitive, language and social skills. However, previous studies have not considered how the quality of the dialogue influences these outcomes. Addressing this gap, our article introduces a high-inference rating instrument to assess the quality of philosophical dialogue. This instrument features four quality dimensions: Philosophical Richness, Co-construction, Focus, and Restrained Facilitation. It was applied to evaluate 63 class dialogues from a Swiss study involving secondary-school students. The article presents the instrument using excerpts from the study, along with initial validation information, showing its reliability in measuring philosophical dialogue quality. The significance of this research lies in its focus on the quality of philosophical dialogue, an aspect often overlooked in educational settings. By providing a tool to assess this quality, we open up new pathways for analyzing the effectiveness of philosophical dialogues in schools. This is especially relevant as educational systems increasingly recognize the importance of developing students' critical thinking and discussion skills. The findings highlight the potential of high-quality philosophical dialogues to enrich students' educational experiences and offer insights for educators and researchers into enhancing these interactions. This study contributes to a deeper understanding of how philosophical dialogue can be used as a powerful educational tool, not just for engaging students but for fostering meaningful and impactful learning.

A dataset of synthetic art dialogues with ChatGPT

This paper introduces Art_GenEvalGPT, a novel dataset of synthetic dialogues centered on art generated through ChatGPT. Unlike existing datasets focused on conventional art-related tasks, Art_GenEvalGPT delves into nuanced conversations about art, encompassing a wide variety of artworks, artists, and genres, and incorporating emotional interventions, integrating speakers’ subjective opinions and different roles for the conversational agents (e.g., teacher-student, expert guide, anthropic behavior or handling toxic users). Generation and evaluation stages of GenEvalGPT platform are used to create the dataset, which includes 13,870 synthetic dialogues, covering 799 distinct artworks, 378 different artists, and 26 art styles. Automatic and manual assessment proof the high quality of the synthetic dialogues generated. For the profile recovery, promising lexical and semantic metrics for objective and factual attributes are offered. For subjective attributes, the evaluation for detecting emotions or subjectivity in the interventions achieves 92% of accuracy using LLM-self assessment metrics.

Race Dialogues and Potential Application in Clinical Environments: A Scoping Review.

Race dialogues, conversations about race and racism among individuals holding different racial identities, have been proposed as one component of addressing racism in medicine and improving the experience of racially minoritized patients. Drawing on work from several fields, we aimed to assess the scope of the literature on race dialogues and to describe potential benefits, best practices, and challenges of conducting such dialogues. Ultimately, our goal was to explore the potential role of race dialogues in medical education and clinical practice. Our scoping review included articles published prior to June 2, 2022, in the biomedicine, psychology, nursing and allied health, and education literatures. Ultimately, 54 articles were included in analysis, all of which pertained to conversations about race occurring between adults possessing different racial identities. We engaged in an interactive group process to identify key takeaways from each article and synthesize cross-cutting themes. Emergent themes reflected the processes of preparing, leading, and following up race dialogues. Preparing required significant personal introspection, logistical organization, and intentional framing of the conversation. Leading safe and successful race dialogues necessitated trauma-informed practices, addressing microaggressions as they arose, welcoming participation and emotions, and centering the experience of individuals with minoritized identities. Longitudinal experiences and efforts to evaluate the quality of race dialogues were crucial to ensuring meaningful impact. Supporting race dialogues within medicine has the potential to promote a more inclusive and justice-oriented workforce, strengthen relationships amongst colleagues, and improve care for patients with racially minoritized identities. Potential levers for supporting race dialogues include high-quality racial justice curricula at every level of medical education and valuation of racial consciousness in admissions and hiring processes. All efforts to support race dialogues must center and uplift those with racially minoritized identities.

Advancing the In-Class Dialogic Quality: Developing an Artificial Intelligence-Supported Framework for Classroom Dialogue Analysis

Advancing the In-Class Dialogic Quality: Developing an Artificial Intelligence-Supported Framework for Classroom Dialogue Analysis

CERAMIC DESIGN WORKSHOP: A CREATIVE EXPERIENCE THROUGH TERRITORIAL JEWELRY WITH THE FLOR DO BARRO GROUP, ALTO DO MOURA, CARUARU –PERNAMBUCO/BRAZIL

This article presents the results of the Ceramic Design workshop around the theme of territorial jewelry to promote creativity and strengthen the feeling of belonging to a collective of women from the Flor do Barro group in Alto do Moura, a suburb of the city of Caruaru, in the state of Pernambuco-Brazil. The main objective of the workshop was to challenge them to explore other possibilities of forms with clay during the execution of the academic extension project “Clay Flowers: mapping and ideation of the craft production chain”. The workshop was planned and carried out through workshops based on design tools to stimulate the creative and productive capacity of artisans. The processes of Ideation, Generation and Selection of alternatives; Planning, Execution and Detailing of ten products; Prototyping and Testing were used. Experimenting with the Flor do Barro group territory jewelry is a strategy for valuing ceramic knowledge, through design and its dialogic character for the group's sustainability.

I.L. MAYAK AS A REVIEWER OF SCIENTIFIC LITERATURE ON THE HISTORY OF ANCIENT ROME

The subject of this study is a part of the scientific heritage of the Honored Professor of Moscow University, Iya Leonidovna Mayak (1922-2018), represented by her reviews on national and foreign monographs on Roman history, published in 1958-1999. The article deals with I.L. Mayak’s motives for writing the reviews, the methodological foundations of her analysis, her requirements for the source base and the historiographical rating of classical studies, their structure and the logic of presentation. It is noted that I.L. Mayak was opposed to dogmatism in the application of the theory of socio-economic formations as well as a hypercritical attitude to sources related to archaic Rome, the spread of which she considered to be the methodological consequence of Kantianism. It is shown that I.L. Mayak not only monitored the diffi cult process of rehabilitation of the ancient tradition as a source for studying the archaic Rome, but herself actively promoted this process, in particular by means of reviewing other people’s works. Th e study considers the requirements set out by I.L. Mayak for classical studies such as the need to provide a terminological analysis of sources data, to trace changes in the content of concepts over time, to show the possibility of various interpretations of the given facts. In the formulation of theoretical constructions I.L. Mayak considered essential to provide a concept against the background of the concepts introduced by predecessors, and if the problem was debatable, to indicate the view clearly and definitely. The analysis of reviews written by Iya Leonidovna allows us to conclude that they make it possible to expand our understanding of her academic views, especially on those problems of Roman history, which she did not directly examine in her monographs and articles, in particular, on the issue of preserving polis paradigm in the late Roma n Empire. Reviews by I.L. Mayak reflect her image memorable to many generations of historians: she was respectful to colleagues, however critical of their work, delicate in remarks, stringently academic in expressing her thoughts. The article shows the polemic sharpness and dialogic character of the reviews by I.L. Mayak.

Graph-based dynamic attribute clipping for conversational recommendation

Conversational recommender systems (CRS) enable traditional recommender systems to interact with users by asking questions about their preferences and recommending items. Conversation recommendation has made significant progress, however, studies on attribute-aware conversational recommendation have overlooked the problem that after obtaining the candidate attribute set, the relevance of the attributes in the candidate attribute set to the user’s current preferred attributes is not further considered, resulting in the existence of many user-uninterested attributes in the candidate attribute set. This seriously affects the dialogue quality and reduces the user’s patience, decreasing recommendation accuracy. To address this problem, this paper proposes a new framework called Attribute Clipping based on Dynamic Graph (ACDG). In ACDG, firstly, the reasoning module uses the restriction property of graph structure to obtain a large set of candidate attributes, and then the attribute clipping module filters out the attributes with high relevance to the current user’s preferred attributes. Thus, ACDG can obtain a better-quality set of candidate attributes. Through extensive experiments on four benchmark CRS datasets, we validate the effectiveness of the method.

The Transition from Face-to-Face Counseling to Videoconferencing Following the Onset of the COVID-19 Pandemic in Taiwan: The Client's Perspective

<p>COVID-19疫情嚴重威脅人們的身心健康，也加速通訊諮商的發展。原進行實體諮商的當事人，面對突發疫情須轉為視訊晤談，這轉換過程的經驗、對諮商關係的知覺，是本研究探究焦點。本研究以發現式研究取向，針對九位大學生當事人，透過半結構式深度訪談蒐集資料，並採紮根理論研究的資料分析方法。研究結果發現，當事人在轉換過程的經驗有四個主題，一是對視訊晤談的預想，正面期待與擔憂參半；二是視訊晤談過程實際困境，包含溝通品質不佳影響投入、虛擬空間療癒氛圍難以營造、情緒表達與覺察受限等，此一主題也是敘說最豐富的；三是有助持續視訊晤談的因素，包含當事人務實的考量、視訊困境的應對與調適；四是視訊晤談的正向經驗，包含省時便利、降低社交接觸的負擔。當事人對於轉換過程諮商關係的知覺有兩個主題，一是轉換對諮商關係的影響，包含情感連結的減損、諮商關係更親近；二是有助諮商關係維繫的因素，包含原有實體諮商基礎的加持、心理師即時的支持與回應。本研究認為在視訊晤談前準備度不足，是導致當事人衝擊經驗的主因之一，而當事人與心理師因應視訊形式的雙向調整有助於當事人調適視訊困境，此外，當事人在轉換過程普遍經歷情感連結的弱化，然原有實體諮商關係的基礎有助於調節轉換過程的不適。最後，依研究結果，提供相關實務與未來研究之建議。</p> <p> </p><p>The global COVID-19 pandemic was a serious threat to the physical and mental health of individuals. Due to social distancing measures, psychological counseling sessions that were previously held face-to-face had to be conducted through videoconferencing. In Taiwan, the two COVID-19 outbreaks in early 2020 and May 2021 necessitated the imposition of social restrictions. This study focuses on the experiences and views of college student clients who initially received counseling for mental health issues through face-to-face sessions but had to transition to online video counseling due to the epidemic.</p> <p>In this study, a qualitative research method with discovery orientation was adopted. The recruitment of study participants was carried out in two phases. The first phase targeted two universities in central Taiwan, while the second phase was expanded to include universities in northern and southern Taiwan. Both recruitments were promoted online on the school pages of several universities. Over 20 college students signed up in the two stages. After screening by the researchers through telephone and email, only 9 college students (female = 6), all sophomores or juniors, met the study criteria. Data collection was conducted through semi-structured, in-depth interviews conducted through videoconferencing due to social distancing constraints. Open coding, axial coding, and selective coding based on grounded theory research were used for data analysis.</p> <p>The analysis extracted four themes in the participants’ experiences of transition to videoconferencing. The first theme is the anticipation of the videoconference, which includes three sub-themes: feeling a sense of similarity to previous experiences of online social communication or distance learning, having positive expectations due to novelty and convenience, and worrying about the possible limitations of the videoconference or interfering distractions. The second theme addresses the challenges of videoconferences, encompassing three sub-themes: the adverse effects of poor dialogue quality on engagement, difficulties in establishing a comforting atmosphere in virtual spaces, and limitations on emotional expression and awareness. The participants discussed this theme frequently in the interviews. The third theme is related to the elements that enable the success of continuous videoconference interviews, including two sub-themes: pragmatic considerations of the client and coping with and adjusting to videoconferencing difficulties. Fourth, the positive experience of videoconferencing includes two sub-themes: time-saving and convenience, which reduce the burden of social contact. Two themes were identified in the participants’ perception of the counseling relationship during the transition process. One aspect to consider is the impact of transition on the counseling relationship, which includes two sub-themes: loss of emotional connection and a strengthened counseling relationship. The second theme pertains to the factors that contribute to maintaining the consultation relationship, encompassing two sub-themes: the support of an existing face-to-face counseling relationship and the immediate support and response from the counseling psychologist.</p> <p>This study suggests that the absence of proper informed consent by psychological counseling professionals before the videoconference is one of the main factors affecting the client’s experience. The quality of the videoconference session is significantly influenced by communication equipment and the environment. In addition, participants typically spoke of a weakening of the emotional connection in the counseling relationship during the transition process. The original face-to-face counseling relationship foundation helped to alleviate the discomfort of the transition process. Finally, based on the study results, recommendations for practice related to telecounseling and suggestions for future research directions are provided.</p> <p> </p>

Investigating educational dialogue: Variations of dialogue amount and quality among different subjects between early primary and secondary school classrooms

To support student learning throughout their school journey, it is important to investigate the authentic state of educational dialogue both in early primary and secondary school to map the potential variations concerning dialogue. The present study examined educational dialogue in early primary school and secondary school in literacy, mathematics and science lessons. Video-recorded classroom lessons (n = 115 in both grades) of Grade 2 primary school teachers (n = 50) and Grade 9 subject teachers (n = 36) were analysed in terms of the amount, duration, and quality of episodes of educational dialogue. Educational dialogues were found to be typically longer in Grade 9 than in Grade 2. In terms of the quality of educational dialogue, teacher-initiated dialogue of moderate quality occurred more in Grade 9 classrooms, whereas teacher-initiated dialogue of high quality was observed more in Grade 2 classrooms. In Grade 2, both the amount and quality of dialogue varied across subjects, whereas in Grade 9, variation concerning specific subjects was scant. The findings contribute to prior research by suggesting differences in several aspects of educational dialogue between early primary and secondary school. These variations should be considered when supporting students' learning and participation through educational dialogue in different developmental phases and in different subjects.

Exploring Listening Relationship Pattern of Information Approval Process in Science Learning: A Qualitative Investigation Using TBLA (Transcript Based Lesson Analysis)

<p dir="ltr"><span>This study reveals listening relationship patterns in the information approval process used to improve the quality of learning dialogue, especially in science learning. A qualitative method with a case study approach was used to analyze listening relationship patterns in science learning during one semester. A total of 3 science teachers, 31 students, and two academics involved in lesson study for learning communities were selected to capture a mutual listening relationship pattern in receiving information with a natural performance and not tense when observing. Observation, documentation, and clinical interviews were used as data collection techniques. Video and audio recorders were involved as documentation tools for this study. Transcript-based lesson analysis (TBLA) was included in conducting data analysis. The listening relationship patterns analysis results in classical discussion sessions in cycles 1–3, which tend to have semi-equal listening relationship patterns. Meanwhile, the listening relationship pattern in group discussion sessions in cycles 1 to 3 tends to be the isolated listening relationship group pattern. The shift in the pattern of listening relationships in group discussion sessions is caused by several factors, including student collaboration awareness, heterogeneous composition of students, tasks, and questions that challenge students, and appropriate interruptions of teacher direction. The research results provide a reference for reflection on developing teacher professionalism to improve more effective and meaningful learning.</span></p><div><span><br /></span></div>

Productive classroom dialogue and its association with student achievement in knowledge-building environments

The first purpose of the present study was to characterize progressive and metacognitive dialogue in knowledge-building classrooms. The second purpose was to examine the association between the quality of classroom dialogue and students’ learning outcomes, including domain knowledge and conception of collaboration. One hundred thirty college students and their teacher participated in this study. A total of 73 lessons were video-recorded. Qualitative analysis of ­classroom dialogue identified dialogic moves into three categories—articulation and elaboration, building-on and connection, and reflection and coordination. The findings provide a rich illustration of how students engage in metacognitive and progressive dialogue. Quantitative analysis indicated that student engagement in classroom dialogue was positively associated with their domain knowledge and conception of collaboration. The results revealed that considering student involvement in classroom dialogue is essential for understanding how knowledge building occurs in classroom contexts and how collective knowledge and conception of collaboration are developed through classroom dialogue.

Rational Dialogues and Its Constructive Social-Cultural Functions

One of the tools that human civilizations use today to understand each other and resolve misunderstandings is dialogue. Dialogue can reduce social distances and bridge human and cultural gaps. In this research, the social and path-opening functions of dialogue as a bridge between social, political and cultural groups have been discussed. Dialogue is a dynamic process, which has two aspects of collective and social nature. Also, with the logic of dialogue and the method of conversation, it is possible to create a bridge over social, political and ethnic gaps and connect people and groups together. The purpose of writing this article is to explain and describe the functions of dialogue, whether it is possible to fill the social, gender, cultural and cognitive gaps in a society with this method. Today's democratic political systems use dialogue as a communication and cognitive bridge between themselves and the nations. Because there are many similarities between bridge and dialogue, which are also discussed in this article. Due to the fact that dialogue has a collective nature and gathering character, this research with a survey method seeks to know the importance, position and role of dialogue in reducing conflicts in social and cultural relationships. The question is, can this collective character and collection of dialogue prevent the separation and division of people and social groups and reduce misunderstandings towards each other. In addition to the theoretical part of this article, a descriptive-analytical method has been used by distributing the questionnaire. The statistical population of Badakhshan University is considered. The findings of this research indicate that dialogue is one of the appropriate ways to connect social division in a society. Based on the findings, dialogue is like a bridge, which can fill and connect social, linguistic, cultural, ethnic and political gaps. (80%) of the sample population considered the role and importance of dialogue in reducing social misunderstandings, preventing violent social, linguistic and ethnic conflicts.

A Mood Semantic Awareness Model for Emotional Interactive Robots.

The rapid development of natural language processing technology and improvements in computer performance in recent years have resulted in the wide-scale development and adoption of human-machine dialogue systems. In this study, the Icc_dialogue model is proposed to enhance the semantic awareness of moods for emotional interactive robots. Equipped with a voice interaction module, emotion calculation is conducted based on model responses, and rules for calculating users' degree of interest are formulated. By evaluating the degree of interest, the system can determine whether it should transition to a new topic to maintain the user's interest. This model can also address issues such as overly purposeful responses and rigid emotional expressions in generated replies. Simultaneously, this study explores topic continuation after answering a question, the construction of dialogue rounds, keyword counting, and the creation of a target text similarity matrix for each text in the dialogue dataset. The matrix is normalized, weights are assigned, and the final text score is calculated. In the text with the highest score, the content of dialogue continuation is determined by calculating a subsequent sentence with the highest similarity. This resolves the issue in which the conversational bot fails to continue dialogue on a topic after answering a question, instead waiting for the user to voluntarily provide more information, resulting in topic interruption. As described in the experimental section, both automatic and manual evaluations were conducted to validate the significant improvement in the mood semantic awareness model's performance in terms of dialogue quality and user experience.

Actionable conversational quality indicators for improving task-oriented dialog systems

Abstract Automatic dialog systems have become a mainstream part of online customer service. Many such systems are built, maintained, and improved by customer service specialists, rather than dialog systems engineers and computer programmers. As conversations between people and machines become commonplace, it is critical to understand what is working, what is not, and what actions can be taken to reduce the frequency of inappropriate system responses. These analyses and recommendations need to be presented in terms that directly reflect the user experience rather than the internal dialog processing. This paper introduces and explains the use of Actionable Conversational Quality Indicators (ACQIs), which are used both to recognize parts of dialogs that can be improved and to recommend how to improve them. This combines benefits of previous approaches, some of which have focused on producing dialog quality scoring while others have sought to categorize the types of errors the dialog system is making. We demonstrate the effectiveness of using ACQIs on LivePerson internal dialog systems used in commercial customer service applications and on the publicly available LEGOv2 conversational dataset. We report on the annotation and analysis of conversational datasets showing which ACQIs are important to fix in various situations. The annotated datasets are then used to build a predictive model which uses a turn-based vector embedding of the message texts and achieves a 79% weighted average f1-measure at the task of finding the correct ACQI for a given conversation. We predict that if such a model worked perfectly, the range of potential improvement actions a bot-builder must consider at each turn could be reduced by an average of 81%.

Neuro or Symbolic? Fine-tuned Transformer with Unsupervised LDA Topic Clustering for Text Sentiment Analysis

For text sentiment analysis, state-of-the-art neural language models have demonstrated promising performance. However, they lack interpretability, require vast volumes of annotated data, and are typically specialized for tasks. In this paper, we explore a connection between fine-tuned Transformer models and unsupervised LDA approach to cope with text sentiment analysis tasks, inspired by the concept of Neuro-symbolic AI. The Transformer and LDA models are combined as a feature extractor to extract the hidden representations of the input text sequences. Subsequently, we employ a feedforward network to forecast various sentiment analysis tasks, such as multi-label emotion prediction, dialogue quality prediction, and nugget detection. Our proposed method obtains the best results in the NTCIR-16 dialogue evaluation (DialEval-2) task, as well as cutting-edge results in emotional intensity prediction using the Ren_CECps corpus. Extensive experiments show that our proposed method is highly explainable, cost-effective in training, and superior in terms of accuracy and robustness.