Investor sentiment and stock portfolio construction: A study based on the black-litterman model

Abstract

This study integrates the Black-Litterman (BL) model with deep learning techniques to construct a stock portfolio that incorporates investor sentiment. We develop a weighted investor sentiment index using comment data from the Eastmoney Stock Bar for eight representative stocks in the SSE 50 Index. The sentiment index is constructed through both a dictionary-based approach and the BERT model. Long Short-Term Memory (LSTM) networks are then employed to predict stock returns, which are incorporated as investor views into the BL framework for portfolio optimization. Empirical results demonstrate that incorporating investor sentiment significantly enhances stock price prediction accuracy, and the BERT-based sentiment index achieves the lowest prediction error. Within the BL model, the portfolio integrating the BERT sentiment index (BERT_BL) achieves an annualized return of 106.58% during the backtesting period, along with superior risk-adjusted performance metrics: a Sharpe ratio of 2.64, and a Sortino ratio of 4.18. The model remains robust even after accounting for transaction costs, parameter adjustments, and across different market environments. This study validates the application of textual sentiment analysis in quantitative investment, offering a methodological innovation by integrating unstructured data with classical asset allocation models. The findings provide practical insights for investors seeking to optimize portfolio management strategies.

Biomass Distribution and Aboveground Carbon Stock in Green Retaining Walls Covered with Hedera colchica
Turan Yüksek, Filiz Yüksek, Gülcay Ercan Oğuztürk +2
Plants (Basel, Switzerland)1 Oct 2026Peer-reviewedCC BYFull textPlant biologyEurope PMC
Combined Return Synergizes Aboveground Photosynthesis and Subsurface Soil Organic Carbon Stock to Boost Spring Wheat Yield in the Qinghai–Tibet Plateau
Xiaoyan Wang, Nannan Hu, Mingdan Song +2
Plants (Basel, Switzerland)23 Sep 2026Peer-reviewedCC BYFull textPlant biologyEurope PMC
AI from Industry 4.0 to Industry 5.0: Engineering for Social Change—A Synthesis of the Special Issue Portfolio
Ching-Hung Lee, Lingguo Bu, Danni Chang
Applied Sciences26 Oct 2026Peer-reviewedCC BYFull textGeneral biology General chemistryDOAJ
Explainable AI for sentiment analysis of human metapneumovirus (HMPV) using XLNet
Md Shahriar Hossain Apu, Md Saiful Islam, Tanjim Taharat Aurpa +1
PLOS One21 Sep 2026Peer-reviewedCC BY 4.0Full text1 citedNeuroscience Infectious diseasePLOS
Estimasi Perubahan Cadangan Karbon Menggunakan Metode Stock Difference Tahun 2014–2024 di Kawasan Gunung Lawu, Tawangmangu, Jawa Tengah
Fifi Prasetyo, Wahyu Setyaningsih, Heri Tjahjono
Geo-Image Journal1 Aug 2026Peer-reviewedCC BYFull textEcologyDOAJ

Cite

BibTeX RIS

BibTeX

@article{sun2026investor,
  title = {{Investor sentiment and stock portfolio construction: A study based on the black-litterman model}},
  author = {Linan Sun and Boyang Fu and Wenwen Liu},
  journal = {PLOS One},
  year = {2026},
  month = sep,
  doi = {10.1371/journal.pone.0358348},
  url = {https://doi.org/10.1371/journal.pone.0358348},
  note = {CC BY 4.0},
}

RIS

TY  - JOUR
TI  - Investor sentiment and stock portfolio construction: A study based on the black-litterman model
AU  - Linan Sun
AU  - Boyang Fu
AU  - Wenwen Liu
PY  - 2026
DA  - 2026/09/15
JO  - PLOS One
DO  - 10.1371/journal.pone.0358348
UR  - https://doi.org/10.1371/journal.pone.0358348
AB  - This study integrates the Black-Litterman (BL) model with deep learning techniques to construct a stock portfolio that incorporates investor sentiment. We develop a weighted investor sentiment index using comment data from the Eastmoney Stock Bar for eight representative stocks in the SSE 50 Index. The sentiment index is constructed through both a dictionary-based approach and the BERT model. Long Short-Term Memory (LSTM) networks are then employed to predict stock returns, which are incorporated as investor views into the BL framework for portfolio optimization. Empirical results demonstrate that incorporating investor sentiment significantly enhances stock price prediction accuracy, and the BERT-based sentiment index achieves the lowest prediction error. Within the BL model, the portfolio integrating the BERT sentiment index (BERT_BL) achieves an annualized return of 106.58% during the backtesting period, along with superior risk-adjusted performance metrics: a Sharpe ratio of 2.64, and a Sortino ratio of 4.18. The model remains robust even after accounting for transaction costs, parameter adjustments, and across different market environments. This study validates the application of textual sentiment analysis in quantitative investment, offering a methodological innovation by integrating unstructured data with classical asset allocation models. The findings provide practical insights for investors seeking to optimize portfolio management strategies.
SN  - 1932-6203
ER  -

Abstract

Related

Cite