Digital Technology and Social Work: Utilizing Chatbots for Testing and Assessment
Bibliographic record
Abstract
This dissertation explores the integration of chatbots into social work practice, aiming to advance professional practice and improve service delivery. With the ability to leverage pre-trained large language models (LLMs) for translation and question-answering systems, chatbots present a promising opportunity to assist social workers in conducting psychological testing and intake assessments. This research addresses three central questions: (1) What are social workers’ attitudes toward chatbots providing social work services? (2) Is there any significant difference between using a chatbot and a pen-and-paper test for psychological testing? And, (3) What is the experience of using chatbots for psychological testing and assessment?To answer these questions, three studies were conducted. The first study employed a qualitative research design, conducting semi-structured one-on-one online interviews with 45 social workers from different cities in China. Thematic analysis revealed that chatbots can simplify document-related tasks, enhance information gathering, provide psychological support, and assist with administrative tasks. However, limitations such as a lack of empathy, inability to adapt to individualized needs, language barriers, and inability to provide physical care were also identified. Additionally, participants expressed concerns about ethical risks such as data security, unemployment risk, and social alienation. The second study investigated the equivalence between chatbot-aided and paper-and-pencil depression symptom testing. Eighty-eight participants were recruited and divided into two groups, with each group undergoing both testing methods in a counterbalanced order. The results indicated no significant difference between the outcomes of the chatbot-aided test and the paper-and-pencil test. This suggests that chatbot-based psychological assessments can be a reliable alternative to traditional methods, while also highlighting new influencing factors such as comprehension issues and linguistic challenges. The third study examined the service user experience of psychological assessments by chatbots, drawing on three theoretical frameworks: Technology Acceptance Model (TAM), Expectation-Confirmation Theory (ECT), and Social Penetration Theory (SPT). A total of 140 participants aged 18–57 were recruited and conducted a psychological assessment with a rule-based chatbot. Data collected through semi-structured interviews were analyzed using deductive and inductive coding. The results showed that participants found the chatbot easy to use and effective in reducing social pressure in self-disclosure. However, concerns about functional limitations, such as lack of follow-up support and diagnostic validity, were also expressed. Furthermore, participants’ willingness to use chatbots was influenced by external factors like institutional and public opinion endorsements. Collectively, these studies demonstrate that chatbots have the potential to enhance the efficiency of social work practice and expand service accessibility. However, careful consideration must be given to technological limitations, ethical frameworks, and cultural contexts to ensure that chatbots complement rather than replace the unique contributions of social workers. Future research should continue to explore the applications of chatbots in social work, addressing the identified limitations and ethical concerns to fully realize the benefits of this technology in the field.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.018 | 0.039 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.003 | 0.003 |
| Scholarly communication | 0.004 | 0.006 |
| Open science | 0.002 | 0.005 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".